To see the other types of publications on this topic, follow the link: Geometry priors.
Journal articles on the topic 'Geometry priors'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Geometry priors.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Guo, Xiaomeng, Li Yi, Hang Zou, and Yining Gao. "Generative Facial Prior for Large-Factor Blind Face Super-Resolution." Journal of Physics: Conference Series 2078, no. 1 (November 1, 2021): 012045. http://dx.doi.org/10.1088/1742-6596/2078/1/012045.
Full textAbstract:
Abstract Most existing face super-resolution (SR) methods are developed based on an assumption that the degradation is fixed and known (e.g., bicubic down sampling). However, these methods suffer a severe performance drop in various unknown degradations in real-world applications. Previous methods usually rely on facial priors, such as facial geometry prior or reference prior, to restore realistic face details. Nevertheless, low-quality inputs cannot provide accurate geometric priors while high-quality references are often unavailable, which limits the use of face super-resolution in real-world scenes. In this work, we propose GPLSR which used the rich priors encapsulated in the pre-trained face GAN network to perform blind face super-resolution. This generative facial priori is introduced into the face super-resolution process through channel squeeze-and-excitation spatial feature transformation layer (SE-SFT), which makes our method achieve a good balance between realness and fidelity. Moreover, GPLSR can restores facial details with single forward pass because of powerful generative facial prior information. Extensive experiment shows that when the magnification factor is 16, this method achieves better performance than existing techniques in both synthetic and real datasets.
2
Goldman, Yehonatan, Ehud Rivlin, and Ilan Shimshoni. "Robust epipolar geometry estimation using noisy pose priors." Image and Vision Computing 67 (November 2017): 16–28. http://dx.doi.org/10.1016/j.imavis.2017.09.006.
Full text
3
Huang, Han, Yulun Wu, Junsheng Zhou, Ge Gao, Ming Gu, and Yu-Shen Liu. "NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 3 (March 24, 2024): 2312–20. http://dx.doi.org/10.1609/aaai.v38i3.28005.
Full textAbstract:
Recently, neural implicit functions have demonstrated remarkable results in the field of multi-view reconstruction. However, most existing methods are tailored for dense views and exhibit unsatisfactory performance when dealing with sparse views. Several latest methods have been proposed for generalizing implicit reconstruction to address the sparse view reconstruction task, but they still suffer from high training costs and are merely valid under carefully selected perspectives. In this paper, we propose a novel sparse view reconstruction framework that leverages on-surface priors to achieve highly faithful surface reconstruction. Specifically, we design several constraints on global geometry alignment and local geometry refinement for jointly optimizing coarse shapes and fine details. To achieve this, we train a neural network to learn a global implicit field from the on-surface points obtained from SfM and then leverage it as a coarse geometric constraint. To exploit local geometric consistency, we project on-surface points onto seen and unseen views, treating the consistent loss of projected features as a fine geometric constraint. The experimental results with DTU and BlendedMVS datasets in two prevalent sparse settings demonstrate significant improvements over the state-of-the-art methods.
4
PRANEETH RACHARLA, SHARATH CHANDRA YERVA, SANJAY RAVULA, and DR.P.ILA CHANDANA KUMARI. "IMAGE RECONSTRUCTION OF OLD DAMAGED PHOTOS." international journal of engineering technology and management sciences 8, no. 3 (2024): 70–74. http://dx.doi.org/10.46647/ijetms.2024.v08i03.009.
Full textAbstract:
In order to restore accurate and realistic details, blind face restoration often uses facial priors, such as a reference prior or a facial geometry prior. The applicability to real-world situations is, however, constrained by the inaccessibility of high quality references and the inability of very low-quality inputs to provide accurate geometric prior. In this paper, we present a GFP-GAN for blind face restoration that takes advantage of rich and varied priors included in a pre-trained face GAN. By the use of spatial feature transform layers, this Generative Facial Prior (GFP) is incorporated into the face restoration process, enabling our method to successfully strike a compromise between realism and fidelity. Whereas GAN inversion methods require image-specific tweaking at inference, our GFP-GAN could simultaneously restore facial details and enhance colours with just a single forward pass because of the powerful generative facial prior and delicate designs. Many tests demonstrate that, on both synthetic and realworld datasets, our technique outperforms earlier art.
5
Nguyen, Ngoc Hung. "Optimal Geometry Analysis for Target Localization With Bayesian Priors." IEEE Access 9 (2021): 33419–37. http://dx.doi.org/10.1109/access.2021.3056440.
Full text
6
Langlois, Thomas A., Nori Jacoby, Jordan W. Suchow, and Thomas L. Griffiths. "Serial reproduction reveals the geometry of visuospatial representations." Proceedings of the National Academy of Sciences 118, no. 13 (March 26, 2021): e2012938118. http://dx.doi.org/10.1073/pnas.2012938118.
Full textAbstract:
An essential function of the human visual system is to locate objects in space and navigate the environment. Due to limited resources, the visual system achieves this by combining imperfect sensory information with a belief state about locations in a scene, resulting in systematic distortions and biases. These biases can be captured by a Bayesian model in which internal beliefs are expressed in a prior probability distribution over locations in a scene. We introduce a paradigm that enables us to measure these priors by iterating a simple memory task where the response of one participant becomes the stimulus for the next. This approach reveals an unprecedented richness and level of detail in these priors, suggesting a different way to think about biases in spatial memory. A prior distribution on locations in a visual scene can reflect the selective allocation of coding resources to different visual regions during encoding (“efficient encoding”). This selective allocation predicts that locations in the scene will be encoded with variable precision, in contrast to previous work that has assumed fixed encoding precision regardless of location. We demonstrate that perceptual biases covary with variations in discrimination accuracy, a finding that is aligned with simulations of our efficient encoding model but not the traditional fixed encoding view. This work demonstrates the promise of using nonparametric data-driven approaches that combine crowdsourcing with the careful curation of information transmission within social networks to reveal the hidden structure of shared visual representations.
7
Bernardo, Jose M. "[The Geometry of Asymptotic Inference]: Comment: On Multivariate Jeffreys' Priors." Statistical Science 4, no. 3 (August 1989): 227–29. http://dx.doi.org/10.1214/ss/1177012483.
Full text
8
Zhang, Xin, and Andrew Curtis. "Bayesian full-waveform inversion with realistic priors." GEOPHYSICS 86, no. 5 (August 30, 2021): A45—A49. http://dx.doi.org/10.1190/geo2021-0118.1.
Full textAbstract:
Seismic full-waveform inversion (FWI) uses full seismic records to estimate the subsurface velocity structure. This requires a highly nonlinear and nonunique inverse problem to be solved; therefore, Bayesian methods have been used to quantify uncertainties in the solution. Variational Bayesian inference uses optimization to efficiently provide solutions. However, previously the method has only been applied to a transmission FWI problem and with strong prior information imposed on the velocity such as is never available in practice. We have found that the method works well in a seismic reflection setting and with realistically weak prior information, representing the type of problem that occurs in reality. We conclude that the method can produce high-resolution images and reliable uncertainties using data from standard reflection seismic acquisition geometry, realistic nonlinearity, and practically achievable prior information.
9
Zhou, Zhongxian, Jianchen Liu, Miaomiao Feng, and Yuwei Cong. "Surveillance Video Georeference Method Based on Real Scene Model with Geometry Priors." Remote Sensing 15, no. 17 (August 28, 2023): 4217. http://dx.doi.org/10.3390/rs15174217.
Full textAbstract:
With the comprehensive promotion of digital construction in China, cameras scattered throughout the country are of great significance in obtaining first-hand data. However, their potential role is limited due to the lack of georeference information on current surveillance cameras. Provided surveillance camera images and real scenes are combined and given georeference information, this problem can be solved, allowing cameras to generate significant social benefits. This article proposed an accurate registration method based on misalignment calibration and least squares matching between real scene and surveillance camera images to address this issue. Firstly, it is necessary to convert the navigation coordinate system from which cameras obtain data to the photogrammetric coordinate system and then solve for the misalignment and internal orientation elements of the camera. Then, accurate registration is achieved using the least squares matching on pyramid images. The experiment obtained surrounding image data of two common scenes with lens pitch angles of 45°, 55°, 65°, 75°, and 85° using the surveillance camera and obtained a 3D real scene model of each scene using a low-altitude aircraft. The experiment results show that the proposed method in this paper can achieve the expected goals of accurately matching real scene and surveillance camera images and assigning georeference information. Through extensive data analysis, the success rate and accuracy rate of registration are 98.1% and 97.06%, respectively.
10
Lee, Se Yoon. "The Use of a Log-Normal Prior for the Student t-Distribution." Axioms 11, no. 9 (September 8, 2022): 462. http://dx.doi.org/10.3390/axioms11090462.
Full textAbstract:
It is typically difficult to estimate the number of degrees of freedom due to the leptokurtic nature of the Student t-distribution. Particularly in studies with small sample sizes, special care is needed concerning prior choice in order to ensure that the analysis is not overly dominated by any prior distribution. In this article, popular priors used in the existing literature are examined by characterizing their distributional properties on an effective support where it is desirable to concentrate on most of the prior probability mass. Additionally, we suggest a log-normal prior as a viable prior option. We show that the Bayesian estimator based on a log-normal prior compares favorably to other Bayesian estimators based on the priors previously proposed via simulation studies and financial applications.
11
Shemyakin, Arkady. "Hellinger Information Matrix and Hellinger Priors." Entropy 25, no. 2 (February 13, 2023): 344. http://dx.doi.org/10.3390/e25020344.
Full textAbstract:
Hellinger information as a local characteristic of parametric distribution families was first introduced in 2011. It is related to the much older concept of the Hellinger distance between two points in a parametric set. Under certain regularity conditions, the local behavior of the Hellinger distance is closely connected to Fisher information and the geometry of Riemann manifolds. Nonregular distributions (non-differentiable distribution densities, undefined Fisher information or denisities with support depending on the parameter), including uniform, require using analogues or extensions of Fisher information. Hellinger information may serve to construct information inequalities of the Cramer–Rao type, extending the lower bounds of the Bayes risk to the nonregular case. A construction of non-informative priors based on Hellinger information was also suggested by the author in 2011. Hellinger priors extend the Jeffreys rule to nonregular cases. For many examples, they are identical or close to the reference priors or probability matching priors. Most of the paper was dedicated to the one-dimensional case, but the matrix definition of Hellinger information was also introduced for higher dimensions. Conditions of existence and the nonnegative definite property of Hellinger information matrix were not discussed. Hellinger information for the vector parameter was applied by Yin et al. to problems of optimal experimental design. A special class of parametric problems was considered, requiring the directional definition of Hellinger information, but not a full construction of Hellinger information matrix. In the present paper, a general definition, the existence and nonnegative definite property of Hellinger information matrix is considered for nonregular settings.
12
Cohen, Fernand, Zexi Liu, and Taslidere Ezgi. "Virtual reconstruction of archeological vessels using expert priors and intrinsic differential geometry information." Computers & Graphics 37, no. 1-2 (February 2013): 41–53. http://dx.doi.org/10.1016/j.cag.2012.11.001.
Full text
13
Zou, Zixin, Weihao Cheng, Yan-Pei Cao, Shi-Sheng Huang, Ying Shan, and Song-Hai Zhang. "Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 7 (March 24, 2024): 7900–7908. http://dx.doi.org/10.1609/aaai.v38i7.28626.
Full textAbstract:
Reconstructing 3D objects from extremely sparse views is a long-standing and challenging problem. While recent techniques employ image diffusion models for generating plausible images at novel viewpoints or for distilling pre-trained diffusion priors into 3D representations using score distillation sampling (SDS), these methods often struggle to simultaneously achieve high-quality, consistent, and detailed results for both novel-view synthesis (NVS) and geometry. In this work, we present Sparse3D, a novel 3D reconstruction method tailored for sparse view inputs. Our approach distills robust priors from a multiview-consistent diffusion model to refine a neural radiance field. Specifically, we employ a controller that harnesses epipolar features from input views, guiding a pre-trained diffusion model, such as Stable Diffusion, to produce novel-view images that maintain 3D consistency with the input. By tapping into 2D priors from powerful image diffusion models, our integrated model consistently delivers high-quality results, even when faced with open-world objects. To address the blurriness introduced by conventional SDS, we introduce the category-score distillation sampling (C-SDS) to enhance detail. We conduct experiments on CO3DV2 which is a multi-view dataset of real-world objects. Both quantitative and qualitative evaluations demonstrate that our approach outperforms previous state-of-the-art works on the metrics regarding NVS and geometry reconstruction.
14
Wang, Kun, Zhiqiang Yan, Huang Tian, Zhenyu Zhang, Xiang Li, Jun Li, and Jian Yang. "AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 6 (March 24, 2024): 5508–16. http://dx.doi.org/10.1609/aaai.v38i6.28360.
Full textAbstract:
Neural Radiance Fields (NeRF) have shown promise in generating realistic novel views from sparse scene images. However, existing NeRF approaches often encounter challenges due to the lack of explicit 3D supervision and imprecise camera poses, resulting in suboptimal outcomes. To tackle these issues, we propose AltNeRF---a novel framework designed to create resilient NeRF representations using self-supervised monocular depth estimation (SMDE) from monocular videos, without relying on known camera poses. SMDE in AltNeRF masterfully learns depth and pose priors to regulate NeRF training. The depth prior enriches NeRF's capacity for precise scene geometry depiction, while the pose prior provides a robust starting point for subsequent pose refinement. Moreover, we introduce an alternating algorithm that harmoniously melds NeRF outputs into SMDE through a consistence-driven mechanism, thus enhancing the integrity of depth priors. This alternation empowers AltNeRF to progressively refine NeRF representations, yielding the synthesis of realistic novel views. Extensive experiments showcase the compelling capabilities of AltNeRF in generating high-fidelity and robust novel views that closely resemble reality.
15
Levitan, Emanuel, Michael Chan, and Gabor T. Herman. "Image-Modeling Gibbs Priors." Graphical Models and Image Processing 57, no. 2 (March 1995): 117–30. http://dx.doi.org/10.1006/gmip.1995.1013.
Full text
16
Khooriphan, Wansiri, Sa-Aat Niwitpong, and Suparat Niwitpong. "Confidence Intervals for the Ratio of Variances of Delta-Gamma Distributions with Applications." Axioms 11, no. 12 (November 30, 2022): 689. http://dx.doi.org/10.3390/axioms11120689.
Full textAbstract:
Since rainfall data often contain zero observations, the ratio of the variances of delta-gamma distributions can be used to compare the rainfall dispersion between two rainfall datasets. To this end, we constructed the confidence interval for the ratio of the variances of two delta-gamma distributions by using the fiducial quantity method, Bayesian credible intervals based on the Jeffreys, uniform, or normal-gamma-beta priors, and highest posterior density (HPD) intervals based on the Jeffreys, uniform, or normal-gamma-beta priors. The performances of the proposed confidence interval methods were evaluated in terms of their coverage probabilities and average lengths via Monte Carlo simulation. Our findings show that the HPD intervals based on Jeffreys prior and the normal-gamma-beta prior are both suitable for datasets with a small and large probability of containing zeros, respectively. Rainfall data from Phrae province, Thailand, are used to illustrate the practicability of the proposed methods with real data.
17
Shao, Yiting, Fei Song, Wei Gao, Shan Liu, and Ge Li. "Texture-Guided Graph Transform Optimization for Point Cloud Attribute Compression." Applied Sciences 14, no. 10 (May 11, 2024): 4094. http://dx.doi.org/10.3390/app14104094.
Full textAbstract:
There is a pressing need across various applications for efficiently compressing point clouds. While the Moving Picture Experts Group introduced the geometry-based point cloud compression (G-PCC) standard, its attribute compression scheme falls short of eliminating signal frequency-domain redundancy. This paper proposes a texture-guided graph transform optimization scheme for point cloud attribute compression. We formulate the attribute transform coding task as a graph optimization problem, considering both the decorrelation capability of the graph transform and the sparsity of the optimized graph within a tailored joint optimization framework. First, the point cloud is reorganized and segmented into local clusters using a Hilbert-based scheme, enhancing spatial correlation preservation. Second, the inter-cluster attribute prediction and intra-cluster prediction are conducted on local clusters to remove spatial redundancy and extract texture priors. Third, the underlying graph structure in each cluster is constructed in a joint rate–distortion–sparsity optimization process, guided by geometry structure and texture priors to achieve optimal coding performance. Finally, point cloud attributes are efficiently compressed with the optimized graph transform. Experimental results show the proposed scheme outperforms the state of the art with significant BD-BR gains, surpassing G-PCC by 31.02%, 30.71%, and 32.14% in BD-BR gains for Y, U, and V components, respectively. Subjective evaluation of the attribute reconstruction quality further validates the superiority of our scheme.
18
Wang, Qianqian, Junhao Song, Chenxi Du, and Chen Wang. "Online Scene Semantic Understanding Based on Sparsely Correlated Network for AR." Sensors 24, no. 14 (July 22, 2024): 4756. http://dx.doi.org/10.3390/s24144756.
Full textAbstract:
Real-world understanding serves as a medium that bridges the information world and the physical world, enabling the realization of virtual–real mapping and interaction. However, scene understanding based solely on 2D images faces problems such as a lack of geometric information and limited robustness against occlusion. The depth sensor brings new opportunities, but there are still challenges in fusing depth with geometric and semantic priors. To address these concerns, our method considers the repeatability of video stream data and the sparsity of newly generated data. We introduce a sparsely correlated network architecture (SCN) designed explicitly for online RGBD instance segmentation. Additionally, we leverage the power of object-level RGB-D SLAM systems, thereby transcending the limitations of conventional approaches that solely emphasize geometry or semantics. We establish correlation over time and leverage this correlation to develop rules and generate sparse data. We thoroughly evaluate the system’s performance on the NYU Depth V2 and ScanNet V2 datasets, demonstrating that incorporating frame-to-frame correlation leads to significantly improved accuracy and consistency in instance segmentation compared to existing state-of-the-art alternatives. Moreover, using sparse data reduces data complexity while ensuring the real-time requirement of 18 fps. Furthermore, by utilizing prior knowledge of object layout understanding, we showcase a promising application of augmented reality, showcasing its potential and practicality.
19
Liu, Pengfei, Liang Xiao, and Tao Li. "A Variational Pan-Sharpening Method Based on Spatial Fractional-Order Geometry and Spectral–Spatial Low-Rank Priors." IEEE Transactions on Geoscience and Remote Sensing 56, no. 3 (March 2018): 1788–802. http://dx.doi.org/10.1109/tgrs.2017.2768386.
Full text
20
Torres-Ruiz, Francisco, Elías Moreno, and Francisco J. Girón. "Intrinsic priors for model comparison in multivariate normal regression." Revista de la Real Academia de Ciencias Exactas, Fisicas y Naturales. Serie A. Matematicas 105, no. 2 (April 23, 2011): 273–89. http://dx.doi.org/10.1007/s13398-011-0033-7.
Full text
21
Zou, Zi-Xin, Shi-Sheng Huang, Tai-Jiang Mu, and Yu-Ping Wang. "ObjectFusion: Accurate object-level SLAM with neural object priors." Graphical Models 123 (September 2022): 101165. http://dx.doi.org/10.1016/j.gmod.2022.101165.
Full text
22
Liu, Yanchao, Jianwei Guo, Bedrich Benes, Oliver Deussen, Xiaopeng Zhang, and Hui Huang. "TreePartNet." ACM Transactions on Graphics 40, no. 6 (December 2021): 1–16. http://dx.doi.org/10.1145/3478513.3480486.
Full textAbstract:
We present TreePartNet , a neural network aimed at reconstructing tree geometry from point clouds obtained by scanning real trees. Our key idea is to learn a natural neural decomposition exploiting the assumption that a tree comprises locally cylindrical shapes. In particular, reconstruction is a two-step process. First, two networks are used to detect priors from the point clouds. One detects semantic branching points, and the other network is trained to learn a cylindrical representation of the branches. In the second step, we apply a neural merging module to reduce the cylindrical representation to a final set of generalized cylinders combined by branches. We demonstrate results of reconstructing realistic tree geometry for a variety of input models and with varying input point quality, e.g., noise, outliers, and incompleteness. We evaluate our approach extensively by using data from both synthetic and real trees and comparing it with alternative methods.
23
Wen, Mingyun, and Kyungeun Cho. "Depth Prior-Guided 3D Voxel Feature Fusion for 3D Semantic Estimation from Monocular Videos." Mathematics 12, no. 13 (July 5, 2024): 2114. http://dx.doi.org/10.3390/math12132114.
Full textAbstract:
Existing 3D semantic scene reconstruction methods utilize the same set of features extracted from deep learning networks for both 3D semantic estimation and geometry reconstruction, ignoring the differing requirements of semantic segmentation and geometry construction tasks. Additionally, current methods allocate 2D image features to all voxels along camera rays during the back-projection process, without accounting for empty or occluded voxels. To address these issues, we propose separating the features for 3D semantic estimation from those for 3D mesh reconstruction. We use a pretrained vision transformer network for image feature extraction and depth priors estimated by a pretrained multi-view stereo-network to guide the allocation of image features within 3D voxels during the back-projection process. The back-projected image features are aggregated within each 3D voxel via averaging, creating coherent voxel features. The resulting 3D feature volume, composed of unified voxel feature vectors, is fed into a 3D CNN with a semantic classification head to produce a 3D semantic volume. This volume can be combined with existing 3D mesh reconstruction networks to produce a 3D semantic mesh. Experimental results on real-world datasets demonstrate that the proposed method significantly increases 3D semantic estimation accuracy.
24
Céspedes-Villar, Yohan, Juan David Martinez-Vargas, and G. Castellanos-Dominguez. "Influence of Patient-Specific Head Modeling on EEG Source Imaging." Computational and Mathematical Methods in Medicine 2020 (April 3, 2020): 1–15. http://dx.doi.org/10.1155/2020/5076865.
Full textAbstract:
Electromagnetic source imaging (ESI) techniques have become one of the most common alternatives for understanding cognitive processes in the human brain and for guiding possible therapies for neurological diseases. However, ESI accuracy strongly depends on the forward model capabilities to accurately describe the subject’s head anatomy from the available structural data. Attempting to improve the ESI performance, we enhance the brain structure model within the individual-defined forward problem formulation, combining the head geometry complexity of the modeled tissue compartments and the prior knowledge of the brain tissue morphology. We validate the proposed methodology using 25 subjects, from which a set of magnetic-resonance imaging scans is acquired, extracting the anatomical priors and an electroencephalography signal set needed for validating the ESI scenarios. Obtained results confirm that incorporating patient-specific head models enhances the performed accuracy and improves the localization of focal and deep sources.
25
Zhang, Xiuming, Pratul P. Srinivasan, Boyang Deng, Paul Debevec, William T. Freeman, and Jonathan T. Barron. "NeRFactor." ACM Transactions on Graphics 40, no. 6 (December 2021): 1–18. http://dx.doi.org/10.1145/3478513.3480496.
Full textAbstract:
We address the problem of recovering the shape and spatially-varying reflectance of an object from multi-view images (and their camera poses) of an object illuminated by one unknown lighting condition. This enables the rendering of novel views of the object under arbitrary environment lighting and editing of the object's material properties. The key to our approach, which we call Neural Radiance Factorization (NeRFactor), is to distill the volumetric geometry of a Neural Radiance Field (NeRF) [Mildenhall et al. 2020] representation of the object into a surface representation and then jointly refine the geometry while solving for the spatially-varying reflectance and environment lighting. Specifically, NeRFactor recovers 3D neural fields of surface normals, light visibility, albedo, and Bidirectional Reflectance Distribution Functions (BRDFs) without any supervision, using only a re-rendering loss, simple smoothness priors, and a data-driven BRDF prior learned from real-world BRDF measurements. By explicitly modeling light visibility, NeRFactor is able to separate shadows from albedo and synthesize realistic soft or hard shadows under arbitrary lighting conditions. NeRFactor is able to recover convincing 3D models for free-viewpoint relighting in this challenging and underconstrained capture setup for both synthetic and real scenes. Qualitative and quantitative experiments show that NeRFactor outperforms classic and deep learning-based state of the art across various tasks. Our videos, code, and data are available at people.csail.mit.edu/xiuming/projects/nerfactor/.
26
Arias-Nicolás, José Pablo, María Isabel Parra, Mario M. Pizarro, and Eva L. Sanjuán. "Bayesian Sensitivity Analysis for VaR and CVaR Employing Distorted Band Priors." Axioms 13, no. 2 (January 24, 2024): 77. http://dx.doi.org/10.3390/axioms13020077.
Full textAbstract:
In the context of robust Bayesian analysis, studies mainly focus on computing the range of some quantities of interest when the prior distribution varies in a class. We use the concept of distorted bands to introduce a family of priors on the shape parameter of the Generalized Pareto distribution. We show how certain properties of the likelihood ratio order allow us to propose novel sensitivity measures for Value at Risk and Conditional Value at Risk, which are the most useful and reliable risk measures. Although we focus on the Generalized Pareto distribution, which is essential in Extreme Value Theory, the new sensitivity measures could be employed for all the distributions that verify certain conditions related to likelihood ratio order. A thorough simulation study was carried out to perform a sensitivity analysis, and two illustrative examples are also provided.
27
Olsen, S. I., and A. Bartoli. "Implicit Non-Rigid Structure-from-Motion with Priors." Journal of Mathematical Imaging and Vision 31, no. 2-3 (February 21, 2008): 233–44. http://dx.doi.org/10.1007/s10851-007-0060-3.
Full text
28
Yan, Xu, Jiantao Gao, Jie Li, Ruimao Zhang, Zhen Li, Rui Huang, and Shuguang Cui. "Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 4 (May 18, 2021): 3101–9. http://dx.doi.org/10.1609/aaai.v35i4.16419.
Full textAbstract:
LiDAR point cloud analysis is a core task for 3D computer vision, especially for autonomous driving. However, due to the severe sparsity and noise interference in the single sweep LiDAR point cloud, the accurate semantic segmentation is non-trivial to achieve. In this paper, we propose a novel sparse LiDAR point cloud semantic segmentation framework assisted by learned contextual shape priors. In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input. By merging multiple frames in the LiDAR sequence as supervision, the optimized SSC module has learned the contextual shape priors from sequential LiDAR data, completing the sparse single sweep point cloud to the dense one. Thus, it inherently improves SS optimization through fully end-to-end training. Besides, a Point-Voxel Interaction (PVI) module is proposed to further enhance the knowledge fusion between SS and SSC tasks, i.e., promoting the interaction of incomplete local geometry of point cloud and complete voxel-wise global structure. Furthermore, the auxiliary SSC and PVI modules can be discarded during inference without extra burden for SS. Extensive experiments confirm that our JS3C-Net achieves superior performance on both SemanticKITTI and SemanticPOSS benchmarks, i.e., 4% and 3% improvement correspondingly.
29
Yang, Dongsheng, Xiaojie Fan, Wei Dong, Chaosheng Huang, and Jun Li. "Robust BEV 3D Object Detection for Vehicles with Tire Blow-Out." Sensors 24, no. 14 (July 9, 2024): 4446. http://dx.doi.org/10.3390/s24144446.
Full textAbstract:
The bird’s-eye view (BEV) method, which is a vision-centric representation-based perception task, is essential and promising for future Autonomous Vehicle perception. It has advantages of fusion-friendly, intuitive, end-to-end optimization and is cheaper than LiDAR. The performance of existing BEV methods, however, would be deteriorated under the situation of a tire blow-out. This is because they quite rely on accurate camera calibration which may be disabled by noisy camera parameters during blow-out. Therefore, it is extremely unsafe to use existing BEV methods in the tire blow-out situation. In this paper, we propose a geometry-guided auto-resizable kernel transformer (GARKT) method, which is designed especially for vehicles with tire blow-out. Specifically, we establish a camera deviation model for vehicles with tire blow-out. Then we use the geometric priors to attain the prior position in perspective view with auto-resizable kernels. The resizable perception areas are encoded and flattened to generate BEV representation. GARKT predicts the nuScenes detection score (NDS) with a value of 0.439 on a newly created blow-out dataset based on nuScenes. NDS can still obtain 0.431 when the tire is completely flat, which is much more robust compared to other transformer-based BEV methods. Moreover, the GARKT method has almost real-time computing speed, with about 20.5 fps on one GPU.
30
Hong, Fangzhou, Mingyuan Zhang, Liang Pan, Zhongang Cai, Lei Yang, and Ziwei Liu. "AvatarCLIP." ACM Transactions on Graphics 41, no. 4 (July 2022): 1–19. http://dx.doi.org/10.1145/3528223.3530094.
Full textAbstract:
3D avatar creation plays a crucial role in the digital age. However, the whole production process is prohibitively time-consuming and labor-intensive. To democratize this technology to a larger audience, we propose AvatarCLIP, a zero-shot text-driven framework for 3D avatar generation and animation. Unlike professional software that requires expert knowledge, AvatarCLIP empowers layman users to customize a 3D avatar with the desired shape and texture, and drive the avatar with the described motions using solely natural languages. Our key insight is to take advantage of the powerful vision-language model CLIP for supervising neural human generation, in terms of 3D geometry, texture and animation. Specifically, driven by natural language descriptions, we initialize 3D human geometry generation with a shape VAE network. Based on the generated 3D human shapes, a volume rendering model is utilized to further facilitate geometry sculpting and texture generation. Moreover, by leveraging the priors learned in the motion VAE, a CLIP-guided reference-based motion synthesis method is proposed for the animation of the generated 3D avatar. Extensive qualitative and quantitative experiments validate the effectiveness and generalizability of AvatarCLIP on a wide range of avatars. Remarkably, AvatarCLIP can generate unseen 3D avatars with novel animations, achieving superior zero-shot capability. Codes are available at https://github.com/hongfz16/AvatarCLIP.
31
Ardid, Alberto, David Dempsey, Edward Bertrand, Fabian Sepulveda, Pascal Tarits, Flora Solon, and Rosalind Archer. "Bayesian magnetotelluric inversion using methylene blue structural priors for imaging shallow conductors in geothermal fields." GEOPHYSICS 86, no. 3 (April 8, 2021): E171—E183. http://dx.doi.org/10.1190/geo2020-0226.1.
Full textAbstract:
In geothermal exploration, magnetotelluric (MT) data and inversion models are commonly used to image shallow conductors typically associated with the presence of an electrically conductive clay cap that overlies the main reservoir. However, these inversion models suffer from nonuniqueness and uncertainty, and the inclusion of useful geologic information is still limited. We have developed a Bayesian inversion method that integrates the electrical resistivity distribution from MT surveys with borehole methylene blue (MeB) data, an indicator of conductive clay content. The MeB data were used to inform structural priors for the MT Bayesian inversion that focus on inferring with uncertainty the shallow conductor boundary in geothermal fields. By incorporating borehole information, our inversion reduced nonuniqueness and then explicitly represented the irreducible uncertainty as estimated depth intervals for the conductor boundary. We used the Markov chain Monte Carlo and a 1D three-layer resistivity model to accelerate the Bayesian inversion of the MT signal beneath each station. Then, inferred conductor boundary distributions were interpolated to construct pseudo-2D/3D models of the uncertain conductor geometry. We compare our approach against deterministic MT inversion software on synthetic and field examples, and our approach has good performance in estimating the depth to the bottom of the conductor, a valuable target in geothermal reservoir exploration.
32
ZOU, YURU, HUAXUAN HU, JIAN LU, XIAOXIA LIU, QINGTANG JIANG, and GUOHUI SONG. "A NONLOCAL LOW-RANK REGULARIZATION METHOD FOR FRACTAL IMAGE CODING." Fractals 29, no. 05 (June 25, 2021): 2150125. http://dx.doi.org/10.1142/s0218348x21501255.
Full textAbstract:
Fractal coding has been widely used as an image compression technique in many image processing problems in the past few decades. On the other hand side, most of the natural images have the characteristic of nonlocal self-similarity that motivates low-rank representations of them. We would employ both the fractal image coding and the nonlocal self-similarity priors to achieve image compression in image denoising problems. Specifically, we propose a new image denoising model consisting of three terms: a patch-based nonlocal low-rank prior, a data-fidelity term describing the closeness of the underlying image to the given noisy image, and a quadratic term measuring the closeness of the underlying image to a fractal image. Numerical results demonstrate the superior performance of the proposed model in terms of peak-signal-to-noise ratio, structural similarity index and mean absolute error.
33
Umetsu, Keiichi, Shutaro Ueda, Bau-Ching Hsieh, Mario Nonino, I.-Non Chiu, Masamune Oguri, Sandor M. Molnar, Anton M. Koekemoer, and Sut-Ieng Tam. "Line-of-sight Elongation and Hydrostatic Mass Bias of the Frontier Fields Galaxy Cluster Abell 370." Astrophysical Journal 934, no. 2 (August 1, 2022): 169. http://dx.doi.org/10.3847/1538-4357/ac7a9e.
Full textAbstract:
Abstract We present a detailed weak-lensing and X-ray study of the Frontier Fields galaxy cluster Abell 370, one of the most massive known lenses on the sky, using wide-field BR C z′ Subaru/Suprime-Cam and Chandra X-ray observations. By combining two-dimensional (2D) shear and azimuthally averaged magnification constraints derived from Subaru data, we perform a lensing mass reconstruction in a free-form manner, which allows us to determine both the radial structure and 2D morphology of the cluster mass distribution. In a triaxial framework assuming a Navarro–Frenk–White density profile, we constrain the intrinsic structure and geometry of the cluster halo by forward modeling the reconstructed mass map. We obtain a halo mass M 200 = (1.54 ± 0.29) ×1015 h −1 M ⊙, a halo concentration c 200 = 5.27 ± 1.28, and a minor–major axis ratio q a = 0.62 ± 0.23 with uninformative priors. Using a prior on the line-of-sight alignment of the halo major axis derived from binary merger simulations constrained by multi-probe observations, we find that the data favor a more prolate geometry with lower mass and lower concentration. From triaxial lens modeling with the line-of-sight prior, we find a spherically enclosed gas mass fraction of f gas = (8.4 ± 1.0)% at 0.7 h −1 Mpc ∼ 0.7r 500. When compared to the hydrostatic mass estimate (M HE) from Chandra observations, our triaxial weak-lensing analysis yields spherically enclosed mass ratios of 1 − b ≡ M HE/M WL = 0.56 ± 0.09 and 0.51 ± 0.09 at 0.7 h −1 Mpc with and without using the line-of-sight prior, respectively. Since the cluster is in a highly disturbed dynamical state, this represents the likely maximum level of hydrostatic bias in galaxy clusters.
34
Shao, Wen-Ze, Qi Ge, Li-Qian Wang, Yun-Zhi Lin, Hai-Song Deng, and Hai-Bo Li. "Nonparametric Blind Super-Resolution Using Adaptive Heavy-Tailed Priors." Journal of Mathematical Imaging and Vision 61, no. 6 (February 27, 2019): 885–917. http://dx.doi.org/10.1007/s10851-019-00876-1.
Full text
35
Abu-Moussa, Mahmoud Hamed, Najwan Alsadat, and Ali Sharawy. "On Estimation of Reliability Functions for the Extended Rayleigh Distribution under Progressive First-Failure Censoring Model." Axioms 12, no. 7 (July 10, 2023): 680. http://dx.doi.org/10.3390/axioms12070680.
Full textAbstract:
When conducting reliability studies, the progressive first-failure censoring (PFFC) method is useful in situations in which the units of the life testing experiment are separated into groups consisting of k units each with the intention of seeing only the first failure in each group. Using progressive first-failure censored samples, the statistical inference for the parameters, reliability, and hazard functions of the extended Rayleigh distribution (ERD) are investigated in this study. The asymptotic normality theory of maximum likelihood estimates (MLEs) is used in order to acquire the maximum likelihood estimates (MLEs) together with the asymptotic confidence intervals (Asym. CIs). Bayesian estimates (BEs) of the parameters and the reliability functions under different loss functions may be produced by using independent gamma informative priors and non-informative priors. The Markov chain Monte Carlo (MCMC) approach is used so that Bayesian computations are performed with ease. In addition, the MCMC method is used in order to create credible intervals (Cred. CIs) for the parameters, which may be used for either informative or non-informative priors. Additionally, computations for the reliability functions are carried out. A Monte Carlo simulation study is carried out in order to provide a comparison of the behaviour of the different estimations that were created for this work. At last, an actual data set is dissected for the purpose of providing an example.
36
Wang, Youhong, Yunji Liang, Hao Xu, Shaohui Jiao, and Hongkai Yu. "SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimation." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 6 (March 24, 2024): 5713–21. http://dx.doi.org/10.1609/aaai.v38i6.28383.
Full textAbstract:
Recently, self-supervised monocular depth estimation has gained popularity with numerous applications in autonomous driving and robotics. However, existing solutions primarily seek to estimate depth from immediate visual features, and struggle to recover fine-grained scene details. In this paper, we introduce SQLdepth, a novel approach that can effectively learn fine-grained scene structure priors from ego-motion. In SQLdepth, we propose a novel Self Query Layer (SQL) to build a self-cost volume and infer depth from it, rather than inferring depth from feature maps. We show that, the self-cost volume is an effective inductive bias for geometry learning, which implicitly models the single-frame scene geometry, with each slice of it indicating a relative distance map between points and objects in a latent space. Experimental results on KITTI and Cityscapes show that our method attains remarkable state-of-the-art performance, and showcases computational efficiency, reduced training complexity, and the ability to recover fine-grained scene details. Moreover, the self-matching-oriented relative distance querying in SQL improves the robustness and zero-shot generalization capability of SQLdepth. Code is available at https://github.com/hisfog/SfMNeXt-Impl.
37
Gouyou Beauchamps, S., F. Lacasa, I. Tutusaus, M. Aubert, P. Baratta, A. Gorce, and Z. Sakr. "Impact of survey geometry and super-sample covariance on future photometric galaxy surveys." Astronomy & Astrophysics 659 (March 2022): A128. http://dx.doi.org/10.1051/0004-6361/202142052.
Full textAbstract:
Photometric galaxy surveys probe the late-time Universe where the density field is highly non-Gaussian. A consequence is the emergence of the super-sample covariance (SSC), a non-Gaussian covariance term that is sensitive to fluctuations on scales larger than the survey window. In this work, we study the impact of the survey geometry on the SSC and, subsequently, on cosmological parameter inference. We devise a fast SSC approximation that accounts for the survey geometry and compare its performance to the common approximation of rescaling the results by the fraction of the sky covered by the survey, fSKY, dubbed ‘full-sky approximation’. To gauge the impact of our new SSC recipe, that we call ‘partial-sky’, we perform Fisher forecasts on the parameters of the (w0, wa)-CDM model in a 3 × 2 point analysis, varying the survey area, the geometry of the mask, and the galaxy distribution inside our redshift bins. The differences in the marginalised forecast errors –with the full-sky approximation performing poorly for small survey areas but excellently for stage-IV-like areas– are found to be absorbed by the marginalisation on galaxy bias nuisance parameters. For large survey areas, the unmarginalised errors are underestimated by about 10% for all probes considered. This is a hint that, even for stage-IV-like surveys, the partial-sky method introduced in this work will be necessary if tight priors are applied on these nuisance parameters. We make the partial-sky method public with a new release of the public code PySSC.
38
Zhang, Longwen, Ziyu Wang, Qixuan Zhang, Qiwei Qiu, Anqi Pang, Haoran Jiang, Wei Yang, Lan Xu, and Jingyi Yu. "CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets." ACM Transactions on Graphics 43, no. 4 (July 19, 2024): 1–20. http://dx.doi.org/10.1145/3658146.
Full textAbstract:
In the realm of digital creativity, our potential to craft intricate 3D worlds from imagination is often hampered by the limitations of existing digital tools, which demand extensive expertise and efforts. To narrow this disparity, we introduce CLAY, a 3D geometry and material generator designed to effortlessly transform human imagination into intricate 3D digital structures. CLAY supports classic text or image inputs as well as 3D-aware controls from diverse primitives (multi-view images, voxels, bounding boxes, point clouds, implicit representations, etc). At its core is a large-scale generative model composed of a multi-resolution Variational Autoencoder (VAE) and a minimalistic latent Diffusion Transformer (DiT), to extract rich 3D priors directly from a diverse range of 3D geometries. Specifically, it adopts neural fields to represent continuous and complete surfaces and uses a geometry generative module with pure transformer blocks in latent space. We present a progressive training scheme to train CLAY on an ultra large 3D model dataset obtained through a carefully designed processing pipeline, resulting in a 3D native geometry generator with 1.5 billion parameters. For appearance generation, CLAY sets out to produce physically-based rendering (PBR) textures by employing a multi-view material diffusion model that can generate 2K resolution textures with diffuse, roughness, and metallic modalities. We demonstrate using CLAY for a range of controllable 3D asset creations, from sketchy conceptual designs to production ready assets with intricate details. Even first time users can easily use CLAY to bring their vivid 3D imaginations to life, unleashing unlimited creativity.
39
Zhang, Longwen, Qiwei Qiu, Hongyang Lin, Qixuan Zhang, Cheng Shi, Wei Yang, Ye Shi, Sibei Yang, Lan Xu, and Jingyi Yu. "DreamFace: Progressive Generation of Animatable 3D Faces under Text Guidance." ACM Transactions on Graphics 42, no. 4 (July 26, 2023): 1–16. http://dx.doi.org/10.1145/3592094.
Full textAbstract:
Emerging Metaverse applications demand accessible, accurate and easy-to-use tools for 3D digital human creations in order to depict different cultures and societies as if in the physical world. Recent large-scale vision-language advances pave the way for novices to conveniently customize 3D content. However, the generated CG-friendly assets still cannot represent the desired facial traits for human characteristics. In this paper, we present Dream-Face, a progressive scheme to generate personalized 3D faces under text guidance. It enables layman users to naturally customize 3D facial assets that are compatible with CG pipelines, with desired shapes, textures and fine-grained animation capabilities. From a text input to describe the facial traits, we first introduce a coarse-to-fine scheme to generate the neutral facial geometry with a unified topology. We employ a selection strategy in the CLIP embedding space to generate coarse geometry, and subsequently optimize both the detailed displacements and normals using Score Distillation Sampling (SDS) from the generic Latent Diffusion Model (LDM). Then, for neutral appearance generation, we introduce a dual-path mechanism, which combines the generic LDM with a novel texture LDM to ensure both the diversity and textural specification in the UV space. We also employ a two-stage optimization to perform SDS in both the latent and image spaces to significantly provide compact priors for fine-grained synthesis. It also enables learning the mapping from the compact latent space into physically-based textures (diffuse albedo, specular intensity, normal maps, etc.). Our generated neutral assets naturally support blendshapes-based facial animations, thanks to the unified geometric topology. We further improve the animation ability with personalized deformation characteristics. To this end, we learn the universal expression prior in a latent space with neutral asset conditioning using the cross-identity hypernetwork, we subsequently train a neural facial tracker from video input space into the pre-trained expression space for personalized fine-grained animation. Extensive qualitative and quantitative experiments validate the effectiveness and generalizability of DreamFace. Notably, DreamFace can generate realistic 3D facial assets with physically-based rendering quality and rich animation ability from video footage, even for fashion icons or exotic characters in cartoons and fiction movies.
40
Jiang, Shijian, Qi Ye, Rengan Xie, Yuchi Huo, Xiang Li, Yang Zhou, and Jiming Chen. "In-Hand 3D Object Reconstruction from a Monocular RGB Video." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 3 (March 24, 2024): 2525–33. http://dx.doi.org/10.1609/aaai.v38i3.28029.
Full textAbstract:
Our work aims to reconstruct a 3D object that is held and rotated by a hand in front of a static RGB camera. Previous methods that use implicit neural representations to recover the geometry of a generic hand-held object from multi-view images achieved compelling results in the visible part of the object. However, these methods falter in accurately capturing the shape within the hand-object contact region due to occlusion. In this paper, we propose a novel method that deals with surface reconstruction under occlusion by incorporating priors of 2D occlusion elucidation and physical contact constraints. For the former, we introduce an object amodal completion network to infer the 2D complete mask of objects under occlusion. To ensure the accuracy and view consistency of the predicted 2D amodal masks, we devise a joint optimization method for both amodal mask refinement and 3D reconstruction. For the latter, we impose penetration and attraction constraints on the local geometry in contact regions. We evaluate our approach on HO3D and HOD datasets and demonstrate that it outperforms the state-of-the-art methods in terms of reconstruction surface quality, with an improvement of 52% on HO3D and 20% on HOD. Project webpage: https://east-j.github.io/ihor.
41
Chu, Mengyu, Lingjie Liu, Quan Zheng, Erik Franz, Hans-Peter Seidel, Christian Theobalt, and Rhaleb Zayer. "Physics informed neural fields for smoke reconstruction with sparse data." ACM Transactions on Graphics 41, no. 4 (July 2022): 1–14. http://dx.doi.org/10.1145/3528223.3530169.
Full textAbstract:
High-fidelity reconstruction of dynamic fluids from sparse multiview RGB videos remains a formidable challenge, due to the complexity of the underlying physics as well as the severe occlusion and complex lighting in the captured data. Existing solutions either assume knowledge of obstacles and lighting, or only focus on simple fluid scenes without obstacles or complex lighting, and thus are unsuitable for real-world scenes with unknown lighting conditions or arbitrary obstacles. We present the first method to reconstruct dynamic fluid phenomena by leveraging the governing physics (ie, Navier -Stokes equations) in an end-to-end optimization from a mere set of sparse video frames without taking lighting conditions, geometry information, or boundary conditions as input. Our method provides a continuous spatio-temporal scene representation using neural networks as the ansatz of density and velocity solution functions for fluids as well as the radiance field for static objects. With a hybrid architecture that separates static and dynamic contents apart, fluid interactions with static obstacles are reconstructed for the first time without additional geometry input or human labeling. By augmenting time-varying neural radiance fields with physics-informed deep learning, our method benefits from the supervision of images and physical priors. Our progressively growing model with regularization further disentangles the density-color ambiguity in the radiance field, which allows for a more robust optimization from the given input of sparse views. A pretrained density-to-velocity fluid model is leveraged in addition as the data prior to avoid suboptimal velocity solutions which underestimate vorticity but trivially fulfill physical equations. Our method exhibits high-quality results with relaxed constraints and strong flexibility on a representative set of synthetic and real flow captures. Code and sample tests are at https://people.mpi-inf.mpg.de/~mchu/projects/PI-NeRF/.
42
Qiu, Yu, and Wenhao Gui. "Statistical Inference for Two Gumbel Type-II Distributions under Joint Type-II Censoring Scheme." Axioms 12, no. 6 (June 8, 2023): 572. http://dx.doi.org/10.3390/axioms12060572.
Full textAbstract:
Comparative lifetime tests are extremely significant when the experimenters study the reliability of the comparative advantages of two products in competition. Considering joint type-II censoring, we deal with the inference when two product lines conform to two Gumbel type-II distributions. The maximum likelihood estimations of Gumbel type-II population parameters were obtained in the current research. An approximate confidence interval and a simultaneous confidence interval based on a Fisher information matrix were also constructed and compared with two bootstrap confidence intervals. Moreover, to evaluate the influence of the prior information, based on the concept of importance sampling, we calculated the Bayesian estimator together with their posterior risks in the case of gamma and non-informative priors under different loss functions. To compare the performances of the overall parameters’ estimator, a Monte Carlo simulation was performed using numerical and graphical methods. Finally, a real data analysis was conducted to verify the accuracy of all the models and methods mentioned.
43
Combettes, Patrick L., Saverio Salzo, and Silvia Villa. "Regularized learning schemes in feature Banach spaces." Analysis and Applications 16, no. 01 (October 26, 2017): 1–54. http://dx.doi.org/10.1142/s0219530516500202.
Full textAbstract:
This paper proposes a unified framework for the investigation of constrained learning theory in reflexive Banach spaces of features via regularized empirical risk minimization. The focus is placed on Tikhonov-like regularization with totally convex functions. This broad class of regularizers provides a flexible model for various priors on the features, including, in particular, hard constraints and powers of Banach norms. In such context, the main results establish a new general form of the representer theorem and the consistency of the corresponding learning schemes under general conditions on the loss function, the geometry of the feature space, and the modulus of total convexity of the regularizer. In addition, the proposed analysis gives new insight into basic tools such as reproducing Banach spaces, feature maps, and universality. Even when specialized to Hilbert spaces, this framework yields new results that extend the state of the art.
44
Garnier, Stephen J., Griff L. Bilbro, James W. Gault, and Wesley E. Snyder. "The effects of various basis image priors on MR Image MAP restoration." Journal of Mathematical Imaging and Vision 5, no. 1 (January 1995): 21–41. http://dx.doi.org/10.1007/bf01250251.
Full text
45
Bergmann, Ronny, Jan Henrik Fitschen, Johannes Persch, and Gabriele Steidl. "Priors with Coupled First and Second Order Differences for Manifold-Valued Image Processing." Journal of Mathematical Imaging and Vision 60, no. 9 (August 13, 2018): 1459–81. http://dx.doi.org/10.1007/s10851-018-0840-y.
Full text
46
Wang, Haixia, Yehao Sun, Zhiguo Zhang, Xiao Lu, and Chunyang Sheng. "Depth estimation for a road scene using a monocular image sequence based on fully convolutional neural network." International Journal of Advanced Robotic Systems 17, no. 3 (May 1, 2020): 172988142092530. http://dx.doi.org/10.1177/1729881420925305.
Full textAbstract:
An advanced driving assistant system is one of the most popular topics nowadays, and depth estimation is an important cue for advanced driving assistant system. Depth prediction is a key problem in understanding the geometry of a road scene for advanced driving assistant system. In comparison to other depth estimation methods using stereo depth perception, determining depth relation using a monocular camera is considerably challenging. In this article, a fully convolutional neural network with skip connection based on a monocular video sequence is proposed. With the integration framework that combines skip connection, fully convolutional network and the consistency between consecutive frames of the input sequence, high-resolution depth maps are obtained with lightweight network training and fewer computations. The proposed method models depth estimation as a regression problem and trains the proposed network using a scale invariance optimization based on L2 loss function, which measures the relationships between points in the consecutive frames. The proposed method can be used for depth estimation of a road scene without the need for any extra information or geometric priors. Experiments on road scene data sets demonstrate that the proposed approach outperforms previous methods for monocular depth estimation in dynamic scenes. Compared with the currently proposed method, our method has achieved good results when using the Eigen split evaluation method. The obvious prominent one is that the linear root mean squared error result is 3.462 and the δ < 1.25 result is 0.892.
47
Kumari, Rani, Yogesh Mani Tripathi, Rajesh Kumar Sinha, and Liang Wang. "Comparison of Estimation Methods for Reliability Function for Family of Inverse Exponentiated Distributions under New Loss Function." Axioms 12, no. 12 (November 29, 2023): 1096. http://dx.doi.org/10.3390/axioms12121096.
Full textAbstract:
In this paper, different estimation is discussed for a general family of inverse exponentiated distributions. Under the classical perspective, maximum likelihood and uniformly minimum variance unbiased are proposed for the model parameters. Based on informative and non-informative priors, various Bayes estimators of the shape parameter and reliability function are derived under different losses, including general entropy, squared-log error, and weighted squared-error loss functions as well as another new loss function. The behavior of the proposed estimators is evaluated through extensive simulation studies. Finally, two real-life datasets are analyzed from an illustration perspective.
48
Cheng, Weihao, Yan-Pei Cao, and Ying Shan. "SparseGNV: Generating Novel Views of Indoor Scenes with Sparse RGB-D Images." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 2 (March 24, 2024): 1308–16. http://dx.doi.org/10.1609/aaai.v38i2.27894.
Full textAbstract:
We study to generate novel views of indoor scenes given sparse input views. The challenge is to achieve both photorealism and view consistency. We present SparseGNV: a learning framework that incorporates 3D structures and image generative models to generate novel views with three modules. The first module builds a neural point cloud as underlying geometry, providing scene context and guidance for the target novel view. The second module utilizes a transformer-based network to map the scene context and the guidance into a shared latent space and autoregressively decodes the target view in the form of discrete image tokens. The third module reconstructs the tokens back to the image of the target view. SparseGNV is trained across a large-scale indoor scene dataset to learn generalizable priors. Once trained, it can efficiently generate novel views of an unseen indoor scene in a feed-forward manner. We evaluate SparseGNV on real-world indoor scenes and demonstrate that it outperforms state-of-the-art methods based on either neural radiance fields or conditional image generation.
49
Lynen, Simon, Bernhard Zeisl, Dror Aiger, Michael Bosse, Joel Hesch, Marc Pollefeys, Roland Siegwart, and Torsten Sattler. "Large-scale, real-time visual–inertial localization revisited." International Journal of Robotics Research 39, no. 9 (July 7, 2020): 1061–84. http://dx.doi.org/10.1177/0278364920931151.
Full textAbstract:
The overarching goals in image-based localization are scale, robustness, and speed. In recent years, approaches based on local features and sparse 3D point-cloud models have both dominated the benchmarks and seen successful real-world deployment. They enable applications ranging from robot navigation, autonomous driving, virtual and augmented reality to device geo-localization. Recently, end-to-end learned localization approaches have been proposed which show promising results on small-scale datasets. However, the positioning accuracy, scalability, latency, and compute and storage requirements of these approaches remain open challenges. We aim to deploy localization at a global scale where one thus relies on methods using local features and sparse 3D models. Our approach spans from offline model building to real-time client-side pose fusion. The system compresses the appearance and geometry of the scene for efficient model storage and lookup leading to scalability beyond what has been demonstrated previously. It allows for low-latency localization queries and efficient fusion to be run in real-time on mobile platforms by combining server-side localization with real-time visual–inertial-based camera pose tracking. In order to further improve efficiency, we leverage a combination of priors, nearest-neighbor search, geometric match culling, and a cascaded pose candidate refinement step. This combination outperforms previous approaches when working with large-scale models and allows deployment at unprecedented scale. We demonstrate the effectiveness of our approach on a proof-of-concept system localizing 2.5 million images against models from four cities in different regions of the world achieving query latencies in the 200 ms range.
50
Subanji, Subanji, Elli Kusumawati, and Indah Setyo Wardhani. "ANALISIS KESALAHAN MAHASISWA PGSD DALAM MEMECAHKAN MASALAH GEOMETRI DITINJAU DARI PRIOR KNOWLEDGE." EDU-MAT: Jurnal Pendidikan Matematika 11, no. 2 (October 31, 2023): 325. http://dx.doi.org/10.20527/edumat.v11i2.17141.
Full textAbstract:
Penelitian ini mengkaji kesalahan mahasiswa dalam memecahkan masalah geometri melalui penelusuran prior knowledge. Penelitian ini merupakan penelitian studi kasus tipe instrumental melibatkan 185 mahasiswa PGSD Universitas Trunojoyo Madura. Subjek menyelesaikan instrumen pelacak prior knowledge dan dilanjutkan pemecahan masalah. Hasil penelitian menunjukkan bahwa 71 (38,37%) gagal menyelesaikan masalah segitiga dan 124 (67,02%) subjek gagal menyelesaikan masalah jajar genjang. Kesalahan menyelesaikan masalah tersebut dikarenakan kesalahan memahami prior knowledge. Kesalahan pemecahan masalah dapat dikelompokkan menjadi empat bentuk yaitu: (1) kesalahan representasi; (2) kesalahan menggambar garis tinggi, (3) kesalahan dalam menggunakan teorema phytagoras, dan (4) kesalahan memahami konteks berbeda. Sebaran kesalahan prior knowledge: 87,75% kesalahan memahami aksioma, definisi dan representasi dalam geometri sebesar; dan 26,49% kesalahan representasi gambar. Kata kunci: Prior Knowladge, Pemecahan Masalah, Geometri Abstract: This study examines students' mistakes in solving geometric problems through searching prior knowledge. This research is an instrumental type case study involving 185 PGSD students at Trunojoyo University, Madura. The subject completed the prior knowledge tracking instrument and continued problem solving. The results showed that 71 (38.37%) failed to solve the triangle problem and 124 (67.02%) subjects failed to solve the parallelogram problem. Errors in solving these problems are due to errors in understanding prior knowledge. Problem solving errors can be grouped into four forms, namely: (1) misrepresentation; (2) mistakes in drawing heights, (3) mistakes in using the Pythagorean theorem, and (4) mistakes in understanding different contexts. Prior knowledge error distribution: 87.75% error in understanding the axioms, definitions and representations in geometry by; and 26.49% image representation error. Keywords: Prior Knowladge, Problem Solving, Geometry.