Bibliographies thématiques / 2D reconstruction

Sommaire

Articles de revues
Thèses
Livres
Chapitres de livres
Actes de conférences

Littérature scientifique sur le sujet « 2D reconstruction »

Auteur : Grafiati

Publié le 25 janvier 2025

Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres

Choisissez une source :

Consultez les listes thématiques d’articles de revues, de livres, de thèses, de rapports de conférences et d’autres sources académiques sur le sujet « 2D reconstruction ».

À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.

Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.

Articles de revues sur le sujet "2D reconstruction"

Van Houten, Elijah E. W., Sajad Ghazavi, Guillaume Fle, Hari s. Nair, Boris Chayer, Ruchi Goswami, Salvatore Girardo, Jochen Guck et Guy Cloutier. « 2D boundary-condition-free nonlinear inversion technique applied to optical shear vibration induced microelastography ». Journal of the Acoustical Society of America 155, n^o 3_Supplement (1 mars 2024) : A246. http://dx.doi.org/10.1121/10.0027380.

Texte intégral

Résumé :

Optical microelastography (OME) has emerged as a new technique for quantifying cellular mechanical properties. However, accurately reconstructing viscoelastic properties at the microscale level from noisy 2D displacement fields remains a challenge. This study introduces a 2D boundary-condition-free nonlinear inversion (2D-NoBC-NLI) approach, addressing challenges of interpreting noisy data and deducing full-field 3D displacements from 2D measurements. OME requires vibrating the cell and mapping the shear modulus based on wave-induced displacements within the cell. The shear modulus distribution is recovered via a coupled adjoint field NLI reconstruction to allow 2D-NoBC-NLI. Validation was conducted through numerical simulations at 36 kHz on a homogeneous sphere of 75 μm diameter and an assigned viscoelastic modulus, G*, of 800 + i150 Pa. The same reconstruction approach was also applied to experimental data obtained from polyacrylamide (PAAm) microbeads of the same diameter. Results demonstrated relative differences from true simulated values of 0.7% and 45% for storage and loss moduli, respectively, with a coefficient of variation under 1% for homogeneous regions. When applying this method to PAAm microbeads, viscoelastic reconstructions showed the potential of OME under experimental conditions. These findings highlight the accuracy of 2D-No BC-NLI reconstruction in OME for precise microscale characterization and mapping of the viscoelastic cell structure.

Styles APA, Harvard, Vancouver, ISO, etc.

Wen, Mingyun, et Kyungeun Cho. « Object-Aware 3D Scene Reconstruction from Single 2D Images of Indoor Scenes ». Mathematics 11, n^o 2 (12 janvier 2023) : 403. http://dx.doi.org/10.3390/math11020403.

Texte intégral

Résumé :

Recent studies have shown that deep learning achieves excellent performance in reconstructing 3D scenes from multiview images or videos. However, these reconstructions do not provide the identities of objects, and object identification is necessary for a scene to be functional in virtual reality or interactive applications. The objects in a scene reconstructed as one mesh are treated as a single object, rather than individual entities that can be interacted with or manipulated. Reconstructing an object-aware 3D scene from a single 2D image is challenging because the image conversion process from a 3D scene to a 2D image is irreversible, and the projection from 3D to 2D reduces a dimension. To alleviate the effects of dimension reduction, we proposed a module to generate depth features that can aid the 3D pose estimation of objects. Additionally, we developed a novel approach to mesh reconstruction that combines two decoders that estimate 3D shapes with different shape representations. By leveraging the principles of multitask learning, our approach demonstrated superior performance in generating complete meshes compared to methods relying solely on implicit representation-based mesh reconstruction networks (e.g., local deep implicit functions), as well as producing more accurate shapes compared to previous approaches for mesh reconstruction from single images (e.g., topology modification networks). The proposed method was evaluated on real-world datasets. The results showed that it could effectively improve the object-aware 3D scene reconstruction performance over existing methods.

Styles APA, Harvard, Vancouver, ISO, etc.

Caruana, Matthew, et Joseph G. Vella. « 3D Facial Reconstruction from 2D Portrait Imagery ». Information & ; Security : An International Journal 47, n^o 3 (2020) : 328–40. http://dx.doi.org/10.11610/isij.4724.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Zhu, Linqi, Chong Zhang, Chaomo Zhang, Xueqing Zhou, Zhansong Zhang, Xin Nie, Weinan Liu et Boyuan Zhu. « Challenges and Prospects of Digital Core-Reconstruction Research ». Geofluids 2019 (20 mai 2019) : 1–29. http://dx.doi.org/10.1155/2019/7814180.

Texte intégral

Résumé :

The simulation of various rock properties based on three-dimensional digital cores plays an increasingly important role in oil and gas exploration and development. The accuracy of 3D digital core reconstruction is important for determining rock properties. In this paper, existing 3D digital core-reconstruction methods are divided into two categories: 3D digital cores based on physical experiments and 3D digital core stochastic reconstructions based on two-dimensional (2D) slices. Additionally, 2D slice-based digital core stochastic reconstruction techniques are classified into four types: a stochastic reconstruction method based on 2D slice mathematical-feature statistical constraints, a stochastic reconstruction method based on statistical constraints that are related to 2D slice morphological characteristics, a physics process-based stochastic reconstruction method, and a hybrid stochastic reconstruction method. The progress related to these various stochastic reconstruction methods, the characteristics of constructed 3D digital cores, and the potential of these methods are analysed and discussed in detail. Finally, reasonable prospects are presented based on the current state of this research area. Currently, studies on digital core reconstruction, especially for the 3D digital core stochastic reconstruction method based on 2D slices, are still very rough, and much room for improvement remains. In particular, we emphasize the importance of evaluating functions, multiscale 3D digital cores, multicomponent 3D digital cores, and disciplinary intersection methods in the 3D construction of digital cores. These four directions should provide focus, alongside challenges, for this research area in the future. This review provides important insights into 3D digital core reconstruction.

Styles APA, Harvard, Vancouver, ISO, etc.

Marin, D., S. Ohrhallinger et M. Wimmer. « SIGDT : 2D Curve Reconstruction ». Computer Graphics Forum 41, n^o 7 (octobre 2022) : 25–36. http://dx.doi.org/10.1111/cgf.14654.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Cardoen, Thorsten, Sam Leroux et Pieter Simoens. « Iterative Online 3D Reconstruction from RGB Images ». Sensors 22, n^o 24 (13 décembre 2022) : 9782. http://dx.doi.org/10.3390/s22249782.

Texte intégral

Résumé :

3D reconstruction is the computer vision task of reconstructing the 3D shape of an object from multiple 2D images. Most existing algorithms for this task are designed for offline settings, producing a single reconstruction from a batch of images taken from diverse viewpoints. Alongside reconstruction accuracy, additional considerations arise when 3D reconstructions are used in real-time processing pipelines for applications such as robot navigation or manipulation. In these cases, an accurate 3D reconstruction is already required while the data gathering is still in progress. In this paper, we demonstrate how existing batch-based reconstruction algorithms lead to suboptimal reconstruction quality when used for online, iterative 3D reconstruction and propose appropriate modifications to the existing Pix2Vox++ architecture. When additional viewpoints become available at a high rate, e.g., from a camera mounted on a drone, selecting the most informative viewpoints is important in order to mitigate long term memory loss and to reduce the computational footprint. We present qualitative and quantitative results on the optimal selection of viewpoints and show that state-of-the-art reconstruction quality is already obtained with elementary selection algorithms.

Styles APA, Harvard, Vancouver, ISO, etc.

Cygan, Szymon, et Adriana Specyalska. « Comparison of three methods for reconstructing 3D motion from 2D video recordings for low cost gait analysis systems ». Polish Journal of Medical Physics and Engineering 27, n^o 4 (1 décembre 2021) : 271–77. http://dx.doi.org/10.2478/pjmpe-2021-0032.

Texte intégral

Résumé :

Abstract Purpose: The aim of this study was to quantify the accuracy of 3D trajectory reconstructions performed from two planar video recordings, using three different reconstruction methods. Additionally, the recordings were carried out using easily available equipment, like built-in cellphone cameras, making the methods suitable for low-cost applications. Methods: A setup for 3D motion tracking was constructed and used to acquire 2D video recordings subsequently used to reconstruct the 3D trajectories by 1) merging appropriate coordinates, 2) merging coordinates with proportional scaling, and 3) calculating the 3D position based on markers’ projections on the viewing plane. As experimental verification, two markers moving at a fixed distance of 98.9 cm were used to assess the consistency of results. Next, gait analysis in five volunteers was carried out to quantify the differences resulting from different reconstruction methods. Results: Quantitative evaluation of the investigated 3D trajectories reconstruction methods showed significant differences between those methods, with the worst reconstruction approach resulting in a maximum error of 50% (standard deviation 13%), while the best resulting in a maximum error of 1% (standard deviation 0.44%). The gait analysis results showed differences in mean angles obtained with each reconstruction method reaching only 2°, which can be attributed to the limited measurement volume. Conclusions: Reconstructing 3D trajectory from 2D views without accounting for the “perspective error” results in significant reconstruction errors. The third method described in this study enables a significant reduction of this issue. Combined with the proposed setup, it provides a functional, low-cost gait analysis system.

Styles APA, Harvard, Vancouver, ISO, etc.

Jiye, Ximen, et Shao Zhifeng. « Three-Dimensional Algebraic Reconstruction From Three Mutually Orthogonal Projections ». Proceedings, annual meeting, Electron Microscopy Society of America 43 (août 1985) : 306–7. http://dx.doi.org/10.1017/s0424820100118400.

Texte intégral

Résumé :

The classic reconstruction problem is that of reconstructing a 3D object from its 2D projections /1-5/. It is also well known that the principal difficulty in solving this problem in electron microscopy is that a very large number of independent projections are normally required. Recently it has been shown /3,4/ that if we restrict our attention to binary or Boolean objects, far fewer projections are needed in order to obtain an approximate solution. 2-dimensional solutions of ID projections were demonstrated using only four views and 3-dimensional reconstruction of 2D projections were obtained by dividing the projections into identifiable slices.In the present paper, an algebraic reconstruction technique (ART) has been studied which uses three mutually orthogonal projections.

Styles APA, Harvard, Vancouver, ISO, etc.

Erlandsson, K., et S. E. Strand. « 3D reconstruction for 2D PET ». Nuclear Instruments and Methods in Physics Research Section A : Accelerators, Spectrometers, Detectors and Associated Equipment 391, n^o 2 (juin 1997) : 369–74. http://dx.doi.org/10.1016/s0168-9002(97)00321-5.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Hanhela, Matti, Antti Paajanen, Mikko J. Nissi et Ville Kolehmainen. « Embedded Quantitative MRI T1ρ Mapping Using Non-Linear Primal-Dual Proximal Splitting ». Journal of Imaging 8, n^o 6 (31 mai 2022) : 157. http://dx.doi.org/10.3390/jimaging8060157.

Texte intégral

Résumé :

Quantitative MRI (qMRI) methods allow reducing the subjectivity of clinical MRI by providing numerical values on which diagnostic assessment or predictions of tissue properties can be based. However, qMRI measurements typically take more time than anatomical imaging due to requiring multiple measurements with varying contrasts for, e.g., relaxation time mapping. To reduce the scanning time, undersampled data may be combined with compressed sensing (CS) reconstruction techniques. Typical CS reconstructions first reconstruct a complex-valued set of images corresponding to the varying contrasts, followed by a non-linear signal model fit to obtain the parameter maps. We propose a direct, embedded reconstruction method for T1ρ mapping. The proposed method capitalizes on a known signal model to directly reconstruct the desired parameter map using a non-linear optimization model. The proposed reconstruction method also allows directly regularizing the parameter map of interest and greatly reduces the number of unknowns in the reconstruction, which are key factors in the performance of the reconstruction method. We test the proposed model using simulated radially sampled data from a 2D phantom and 2D cartesian ex vivo measurements of a mouse kidney specimen. We compare the embedded reconstruction model to two CS reconstruction models and in the cartesian test case also the direct inverse fast Fourier transform. The T1ρ RMSE of the embedded reconstructions was reduced by 37–76% compared to the CS reconstructions when using undersampled simulated data with the reduction growing with larger acceleration factors. The proposed, embedded model outperformed the reference methods on the experimental test case as well, especially providing robustness with higher acceleration factors.

Styles APA, Harvard, Vancouver, ISO, etc.

Plus de sources

Thèses sur le sujet "2D reconstruction"

Breton, Rodolphe. « Reconstruction inversible d'objets discrets 2D ». Poitiers, 2003. http://www.theses.fr/2003POIT2305.

Texte intégral

Résumé :

Notre travail s'inscrit dans le cadre de la géométrie discrète, un domaine dans lequel les données manipulées sont discrètes. Ce domaine est souvent associé à celui de la géométrie euclidienne, plus classique. Il est possible de passer du modèle euclidien au modèle discret par une opération nommée discrétisation. L'opération réciproque est appellée reconstruction. Pour les besoins d'un logiciel de modélisation développé au laboratoire SIC, nous nous sommes attaché à réaliser une reconstruction de courbes discrètes standard 2D vérifiant des critères de réversibilité ß la discrétisation d'un objet discret reconstruit donne exactement l'objet discret d'origine ß, d'esthétique ß l'objet reconstruit est aussi proche que possible de ce qu'on attend intuitivement ß et d'unicité ß pour un objet discret donné, la reconstruction sera toujours la même. Notre méthode de reconstruction est basée sur un algorithme de reconnaissance de segments discrets nai͏̈fs conçu par J. Vittone mais utilise le modèle standard, plus adapté à la description de contours dans le modèle inter-pixel
The framework of our thesis is discrete geometry since we handle discrete objects. A Euclidean object can be converted into a discrete one by an operation of discretization. Conversely, the reconstruction allows us to obtain a discrete object from a Euclidean one. We created a reconstruction method for 2D discrete curves and implemented it in a modeling software developped in the SIC laboratory. This method satisfies three criteria : invertibility ß the discretization of the reconstructed object leads to the original discret object ß, aesthetics ß the reconstructed object is as close as possible to what we intuitively expect ß, unicity ß the reconstruction of a given discret object will always give the same Euclidean object. Our reconstruction method is based on an algorithm written by J. Vittone. Although this algorithm is designed to recognize naive discrete segments, we work with standard segments since it is well fitted to describe objects boundaries in the inter-pixel model

Styles APA, Harvard, Vancouver, ISO, etc.

Huang, Hui. « Efficient reconstruction of 2D images and 3D surfaces ». Thesis, University of British Columbia, 2008. http://hdl.handle.net/2429/2821.

Texte intégral

Résumé :

The goal of this thesis is to gain a deep understanding of inverse problems arising from 2D image and 3D surface reconstruction, and to design effective techniques for solving them. Both computational and theoretical issues are studied and efficient numerical algorithms are proposed. The first part of this thesis is concerned with the recovery of 2D images, e.g., de-noising and de-blurring. We first consider implicit methods that involve solving linear systems at each iteration. An adaptive Huber regularization functional is used to select the most reasonable model and a global convergence result for lagged diffusivity is proved. Two mechanisms---multilevel continuation and multigrid preconditioning---are proposed to improve efficiency for large-scale problems. Next, explicit methods involving the construction of an artificial time-dependent differential equation model followed by forward Euler discretization are analyzed. A rapid, adaptive scheme is then proposed, and additional hybrid algorithms are designed to improve the quality of such processes. We also devise methods for more challenging cases, such as recapturing texture from a noisy input and de-blurring an image in the presence of significant noise. It is well-known that extending image processing methods to 3D triangular surface meshes is far from trivial or automatic. In the second part of this thesis we discuss techniques for faithfully reconstructing such surface models with different features. Some models contain a lot of small yet visually meaningful details, and typically require very fine meshes to represent them well; others consist of large flat regions, long sharp edges (creases) and distinct corners, and the meshes required for their representation can often be much coarser. All of these models may be sampled very irregularly. For models of the first class, we methodically develop a fast multiscale anisotropic Laplacian (MSAL) smoothing algorithm. To reconstruct a piecewise smooth CAD-like model in the second class, we design an efficient hybrid algorithm based on specific vertex classification, which combines K-means clustering and geometric a priori information. Hence, we have a set of algorithms that efficiently handle smoothing and regularization of meshes large and small in a variety of situations.

Styles APA, Harvard, Vancouver, ISO, etc.

Henrichsen, Arne. « 3D reconstruction and camera calibration from 2D images ». Master's thesis, University of Cape Town, 2000. http://hdl.handle.net/11427/9725.

Texte intégral

Résumé :

Includes bibliographical references.
A 3D reconstruction technique from stereo images is presented that needs minimal intervention from the user. The reconstruction problem consists of three steps, each of which is equivalent to the estimation of a specific geometry group. The first step is the estimation of the epipolar geometry that exists between the stereo image pair, a process involving feature matching in both images. The second step estimates the affine geometry, a process of finding a special plane in projective space by means of vanishing points. Camera calibration forms part of the third step in obtaining the metric geometry, from which it is possible to obtain a 3D model of the scene. The advantage of this system is that the stereo images do not need to be calibrated in order to obtain a reconstruction. Results for both the camera calibration and reconstruction are presented to verify that it is possible to obtain a 3D model directly from features in the images.

Styles APA, Harvard, Vancouver, ISO, etc.

Zhao, Yajie. « 3D Human Face Reconstruction and 2D Appearance Synthesis ». UKnowledge, 2018. https://uknowledge.uky.edu/cs_etds/66.

Texte intégral

Résumé :

3D human face reconstruction has been an extensive research for decades due to its wide applications, such as animation, recognition and 3D-driven appearance synthesis. Although commodity depth sensors are widely available in recent years, image based face reconstruction are significantly valuable as images are much easier to access and store. In this dissertation, we first propose three image-based face reconstruction approaches according to different assumption of inputs. In the first approach, face geometry is extracted from multiple key frames of a video sequence with different head poses. The camera should be calibrated under this assumption. As the first approach is limited to videos, we propose the second approach then focus on single image. This approach also improves the geometry by adding fine grains using shading cue. We proposed a novel albedo estimation and linear optimization algorithm in this approach. In the third approach, we further loose the constraint of the input image to arbitrary in the wild images. Our proposed approach can robustly reconstruct high quality model even with extreme expressions and large poses. We then explore the applicability of our face reconstructions on four interesting applications: video face beautification, generating personalized facial blendshape from image sequences, face video stylizing and video face replacement. We demonstrate great potentials of our reconstruction approaches on these real-world applications. In particular, with the recent surge of interests in VR/AR, it is increasingly common to see people wearing head-mounted displays. However, the large occlusion on face is a big obstacle for people to communicate in a face-to-face manner. Our another application is that we explore hardware/software solutions for synthesizing the face image with presence of HMDs. We design two setups (experimental and mobile) which integrate two near IR cameras and one color camera to solve this problem. With our algorithm and prototype, we can achieve photo-realistic results. We further propose a deep neutral network to solve the HMD removal problem considering it as a face inpainting problem. This approach doesn't need special hardware and run in real-time with satisfying results.

Styles APA, Harvard, Vancouver, ISO, etc.

Ren, Yuheng. « Implicit shape representation for 2D/3D tracking and reconstruction ». Thesis, University of Oxford, 2014. http://ora.ox.ac.uk/objects/uuid:c70dc663-ee7c-4100-b492-3a85bf8640d1.

Texte intégral

Résumé :

This thesis develops and describes methods for real-time tracking, segmentation and 3-dimensional (3D) model acquisition, in the context of developing games for stroke patients that are rehabilitating at home. Real-time tracking and reconstruction of a stroke patient's feet, hands and the control objects that they are touching can enable not only the graphical visualization of the virtual avatar in the rehabilitation games, but also permits measurement of the patient's performs. Depth or combined colour and depth imagery from a Kinect sensor is used as input data. The 3D signed distance function (SDF) is used as implicit shape representation, and a series of probabilistic graphical models are developed for the problem of model-based 3D tracking, simultaneous 3D tracking and reconstruction and 3D tracking of multiple objects with identical appearance. The work is based on the assumption that the observed imagery is generated jointly by the pose(s) and the shape(s). The depth of each pixel is randomly and independently sampled from the likelihood of the pose(s) and the shape(s). The pose(s) tracking and 3D shape reconstruction problems are then cast as the maximum likelihood (ML) or maximum a posterior (MAP) estimate of the pose(s) or 3D shape. This methodology first leads to a novel probabilistic model for tracking rigid 3D objects with only depth data. For a known 3D shape, optimization aims to find the optimal pose that back projects all object region pixels onto the zero level set of the 3D shape, thus effectively maximising the likelihood of the pose. The method is extended to consider colour information for more robust tracking in the presence of outliers and occlusions. Initialised with a coarse 3D model, the extended method is also able to simultaneously reconstruct and track an unknown 3D object in real time. Finally, the concept of `shape union' is introduced to solve the problem of tracking multiple 3D objects with identical appearance. This is formulated as the minimum value of all SDFs in camera coordinates, which (i) leads to a per-pixel soft membership weight for each object thus providing an elegant solution for the data association in multi-target tracking and (ii) it allows for probabilistic physical constraints that avoid collisions between objects to be naturally enforced. The thesis also explore the possibility of using implicit shape representation for online shape learning. We use the harmonics of 2D discrete cosine transform (DCT) to represent 2D shapes. High frequency harmonics are decoupled from low ones to represent the coarse information and the details of the 2D shape. A regression model is learnt online to model the relationship between the high and low frequency harmonics using Locally Weighted Projection Regression (LWPR). We have demonstrated that the learned regression model is able to detect occlusion and recover them to the complete shape.

Styles APA, Harvard, Vancouver, ISO, etc.

Li, Ci. « Automatic horse lameness detection through 2D to 3D reconstruction ». Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-272126.

Texte intégral

Résumé :

Lameness is a condition that is difficult to treat in horses when discovered too late and is therefore a common cause for culling. Veterinarians often make a diagnosis based on their subjective experience. In this thesis, we investigate whether neural networks can do lameness detection of horses by using the 3D reconstructed model of the horses. We divide the problem into two parts. The first part is about the 3D model reconstruction of the horse in the videos and then we use neural networks to do lameness detection. We also perform experiments on human videos to test the generalization of our idea, reconstructing the 3D human model in the videos and doing action recognition with neural networks. The two frameworks we use are standard LSTM and LSTM with an attention mechanism. The results of the human experiments show that both networks can separate human actions given the 3D human model sequences and some specific joints are pointed out when doing the two-class action classification. The results of animal experiments preliminarily show that the information of the 3D horse model can be used to perform lameness detection and front-limb lameness is more comfortable for the networks to learn compared to hind-limb lameness.
Hälta är ett svårbehandlat tillstånd hos hästar när det upptäcks för sent och är därför en vanlig orsak för avlivning. Veterinärer ställer ofta en diagnos baserat på deras subjektiva erfarenhet. I det här examensarbetet undersöker vi om neurala nätverk kan upptäcka hälta med hjälp av en 3D-rekonstruerad modell av hästar. Vi delar upp problemet i två delar. Den första delen handlar om rekonstruktion av 3D-modellen av hästen i filmerna och sedan använder vi neurala nätverk för att göra hältedetektering. Vi utför också experiment på mänskliga videor för att testa generaliseringen av vår idé, rekonstruerar den mänskliga 3D-modellen i videorna och utför handlingsigenkänning med neurala nätverk. De två sortens nätverk vi använder är ett standard LSTM-nätverk och ett LSTM-nätverk med en uppmärksamhetsmekanism. Resultaten från de mänskliga experimenten visar att båda nätverken kan separera mänskliga handlingar givet 3D-modeller och vissa relevanta kroppsdelar ges uppmärksamhet när man gör actionklassificering över två klasser. Resultaten av försöken på hästdata visar preliminärt att informationen i 3D-hästmodellen kan användas för att utföra hältedetektion och att det är lättare att detektera frambenshälta jämfört med att lära sig att detektera bakbenshälta.

Styles APA, Harvard, Vancouver, ISO, etc.

Rolland, Franck. « Représentation tridimensionnelle et reconstruction 3D à partir de coupes 2D ». Phd thesis, Grenoble 1, 1991. http://tel.archives-ouvertes.fr/tel-00339648.

Texte intégral

Résumé :

L'objectif des travaux présentés dans ce mémoire est la représentation de formes tridimensionnelles ainsi que la reconstruction tridimensionnelle a partir de coupes sériées. Après avoir défini le cadre exact de la reconstruction tridimensionnelle a partir de coupes sériées, le premier chapitre analyse les différentes étapes et les méthodes généralement employées pour effectuer cette reconstruction. Les chapitre 2 et 3 s'attachent a la description et a la représentation de formes tant bidimensionnelles que tridimensionnelles. Le chapitre 3 developpe ainsi une methode de squelettisation tridimensionnelle permettant d'obtenir un squelette filaire. Le chapitre 4 est consacre a la description de deux méthodes de reconstruction tridimensionnelle opérant par inférence de formes. La methode utilisant l'inférence structurelle de graphes de la ligne médiane est ensuite développée. Elle passe par une nécessaire étape, chapitre 5, de mise en correspondance de graphes de la ligne médiane. Différentes méthodes de mise en correspondance sont présentées, finalement la methode procédant par recherche de cliques dans un graphe est développée. La construction du graphe de mise en correspondance est tout d'abord présentée, ensuite la recherche de cliques est abordée a l'aide de méthodes heuristiques de parcours (recuit simule et algorithmes génétiques). Le chapitre 6 développe le processus d'inférence de graphes de la ligne médiane mis en œuvre, il permet d'inférer des coupes intermediaires qui sont empilées pour finalement donner le volume tridimensionnel recherche. Le chapitre 7 est consacre a la présentation des divers résultats et de leurs conséquences, il présenté aussi d'autres applications possibles des différentes techniques developpees

Styles APA, Harvard, Vancouver, ISO, etc.

Li, Yi. « Key issues of 2D/3D image reconstruction in electrical tomography ». Thesis, University of Manchester, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.489019.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Dowell, Rachel J. (Rachel Jean). « Registration of 2D ultrasound images in preparation for 3D reconstruction ». Thesis, Massachusetts Institute of Technology, 1997. http://hdl.handle.net/1721.1/10181.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Cheng, Yuan 1971. « 3D reconstruction from 2D images and applications to cell cytoskeleton ». Thesis, Massachusetts Institute of Technology, 2000. http://hdl.handle.net/1721.1/88870.

Texte intégral

Résumé :

Thesis (Ph.D.)--Massachusetts Institute of Technology, Dept. of Mechanical Engineering, February 2001.
Includes bibliographical references (leaves 121-129).
Approaches to achieve three dimensional (3D) reconstruction from 2D images can be grouped into two categories: computer-vision-based reconstruction and tomographic reconstruction. By exploring both the differences and connections between these two types of reconstruction, the thesis attempts to develop a new technique that can be applied to 3D reconstruction of biological structures. Specific attention is given to the reconstruction of the cell cytoskeleton from electron microscope images. The thesis is composed of two parts. The first part studies computer-vision-based reconstruction methods that extract 3D information from geometric relationship among images. First, a multiple-feature-based stereo reconstruction algorithm that recovers the 3D structure of an object from two images is presented. A volumetric reconstruction method is then developed by extending the algorithm to multiple images. The method integrates a sequence of 3D reconstruction from different stereo pairs. It achieves a globally optimized reconstruction by evaluating certainty values of each stereo reconstruction. This method is tuned and applied to 3D reconstruction of the cell cytoskeleton. Feasibility, reliability and flexibility of the method are explored.
(cont.) The second part of the thesis focuses on a special tomographic reconstruction, discrete tomography, where the object to be reconstructed is composed of a discrete set of materials each with uniform values. A Bayesian labeling process is proposed as a framework for discrete tomography. The process uses an expectation-maximization (EM) algorithm with which the reconstruction is obtained efficiently. Results demonstrate that the proposed algorithm achieves high reconstruction quality even with a small number of projections. An interesting relationship between discrete tomography and conventional tomography is also derived, showing that discrete tomography is a more generalized form of tomography and conventional tomography is only a special case of such generalization.
by Yuan Cheng.
Ph.D.

Styles APA, Harvard, Vancouver, ISO, etc.

Plus de sources

Livres sur le sujet "2D reconstruction"

Reading the Skull : Advanced 2D Reconstruction. Taylor & Francis Group, 2023.

Trouver le texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Reading the Skull : Advanced 2D Reconstruction. CRC Press LLC, 2023.

Trouver le texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Chapitres de livres sur le sujet "2D reconstruction"

Stojanovski, David, Uxio Hermida, Marica Muffoletto, Pablo Lamata, Arian Beqiri et Alberto Gomez. « Efficient Pix2Vox++ for 3D Cardiac Reconstruction from 2D Echo Views ». Dans Simplifying Medical Ultrasound, 86–95. Cham : Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-16902-1_9.

Texte intégral

Résumé :

AbstractAccurate geometric quantification of the human heart is a key step in the diagnosis of numerous cardiac diseases, and in the management of cardiac patients. Ultrasound imaging is the primary modality for cardiac imaging, however acquisition requires high operator skill, and its interpretation and analysis is difficult due to artifacts. Reconstructing cardiac anatomy in 3D can enable discovery of new biomarkers and make imaging less dependent on operator expertise, however most ultrasound systems only have 2D imaging capabilities. We propose both a simple alteration to the Pix2Vox++ networks for a sizeable reduction in memory usage and computational complexity, and a pipeline to perform reconstruction of 3D anatomy from 2D standard cardiac views, effectively enabling 3D anatomical reconstruction from limited 2D data. We evaluate our pipeline using synthetically generated data achieving accurate 3D whole-heart reconstructions (peak intersection over union score $$> 0.88$$ > 0.88 ) from just two standard anatomical 2D views of the heart. We also show preliminary results using real echo images.

Styles APA, Harvard, Vancouver, ISO, etc.

Fang, Lu. « Plenoptic Reconstruction ». Dans Advances in Computer Vision and Pattern Recognition, 75–189. Singapore : Springer Nature Singapore, 2024. http://dx.doi.org/10.1007/978-981-97-6915-5_4.

Texte intégral

Résumé :

AbstractEmpowered by advanced plenoptic sensing systems, light-field imaging becomes one of the most extensively used methods for capturing 3D views of a scene. In contrast to the traditional input to a 3D graphics system, namely, scenes consisting of pre-defined geometric primitives with different materials and sets of lights, the input to a light field is only a set of 2D images which are informative and cost effective. Unfortunately, due to the limited sensor resolution, existing systems must balance the spatial and angular resolution, i.e., one can obtain dense sampling images in the spatial dimension but only sparse sampling images in the angular (viewing angle) dimension or vice versa.

Styles APA, Harvard, Vancouver, ISO, etc.

Tomaževič, Dejan, Boštjan Likar et Franjo Pernuš. « Reconstruction-Based 3D/2D Image Registration ». Dans Lecture Notes in Computer Science, 231–38. Berlin, Heidelberg : Springer Berlin Heidelberg, 2005. http://dx.doi.org/10.1007/11566489_29.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Chan, Chee Fatt, Chee Keong Kwoh, Ming Yeong Teo et Wan Sing Ng. « Tessellated Surface Reconstruction from 2D Contours ». Dans Medical Image Computing and Computer-Assisted Intervention – MICCAI’99, 297–307. Berlin, Heidelberg : Springer Berlin Heidelberg, 1999. http://dx.doi.org/10.1007/10704282_33.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Alvarez-Gutiérrez, Mariana Teresa, Aldo Rodrigo Mejía-Rodríguez, Ines Alejandro Cruz-Guerrero et Edgar Román Arce-Santana. « 3D Kidney Reconstruction from 2D Ultrasound Images ». Dans IFMBE Proceedings, 393–400. Cham : Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-30648-9_51.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Platzer, Esther-S., Frank Deinzer, Dietrich Paulus et Joachim Denzler. « 3D Blood Flow Reconstruction from 2D Angiograms ». Dans Informatik aktuell, 288–92. Berlin, Heidelberg : Springer Berlin Heidelberg, 2008. http://dx.doi.org/10.1007/978-3-540-78640-5_58.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Grellert, Marc, Markus Wacker, Jonas Bruschke, Daniel Beck et Wolfgang Stille. « IDOVIR – A New Infrastructure for Documenting Paradata and Metadata of Virtual Reconstructions ». Dans Lecture Notes in Computer Science, 103–14. Cham : Springer Nature Switzerland, 2024. https://doi.org/10.1007/978-3-031-78590-0_9.

Texte intégral

Résumé :

AbstractIn the context of source-based virtual reconstructions and its underlying decision-making processes (paradata), there has been a long-time demand for documenting why a reconstruction was executed in a certain way, and presenting it in a comprehensible and public manner. Lacking documentation leads to a loss of knowledge and that the scientific nature of a reconstruction won’t be guaranteed anymore. Based on earlier prototypes, TU Darmstadt and HTW Dresden developed IDOVIR (Infrastructure for Documentation of Virtual Reconstructions) which enables the documentation of this kind of paradata and metadata, and, at the same time, supports communication during the reconstruction phase. The tool can be used free of charge and independently by registering via ORCID. The core of IDOVIR is the division of an entity into different spatial areas and time periods to which multiple variants can be assigned. Each variant contains the triple of 1) the representation of the reconstruction (2D or 3D), 2) the sources used, and 3) a textual argumentation that explains how the reconstruction has been inferred from the sources. For long-term storage and availability, IDOVIR is hosted by the University and State Library Darmstadt.

Styles APA, Harvard, Vancouver, ISO, etc.

Weinmann, Martin. « A Brief Survey on 2D and 3D Feature Extraction ». Dans Reconstruction and Analysis of 3D Scenes, 39–53. Cham : Springer International Publishing, 2016. http://dx.doi.org/10.1007/978-3-319-29246-5_3.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Bayro-Corrochano, Eduardo. « Neurocomputing for 2D Contour and 3D Surface Reconstruction ». Dans Geometric Algebra Applications Vol. I, 659–75. Cham : Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-319-74830-6_19.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Liu, Feng, et Xiaoming Liu. « 2D GANs Meet Unsupervised Single-View 3D Reconstruction ». Dans Lecture Notes in Computer Science, 497–514. Cham : Springer Nature Switzerland, 2022. http://dx.doi.org/10.1007/978-3-031-19769-7_29.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Actes de conférences sur le sujet "2D reconstruction"

Ortolani, Francesca. « SMD Coincident Antenna Array for 2D Field Acquisition and Reconstruction ». Dans 2024 International Conference on Electromagnetics in Advanced Applications (ICEAA), 617–20. IEEE, 2024. http://dx.doi.org/10.1109/iceaa61917.2024.10701777.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Makur, Anuran, Elchanan Mossel et Yury Polyanskiy. « Reconstruction on 2D Regular Grids ». Dans 2021 IEEE International Symposium on Information Theory (ISIT). IEEE, 2021. http://dx.doi.org/10.1109/isit45174.2021.9518174.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Zeng, Xiangyan, James Ervin Glover, Owen Hughes et Henning Stahlberg. « 3D reconstruction of 2D crystals ». Dans the 49th Annual Southeast Regional Conference. New York, New York, USA : ACM Press, 2011. http://dx.doi.org/10.1145/2016039.2016084.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Widanagamaachchi, W. N., et A. T. Dharmaratne. « 3D Face Reconstruction from 2D Images ». Dans 2008 Digital Image Computing : Techniques and Applications. IEEE, 2008. http://dx.doi.org/10.1109/dicta.2008.83.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Tao, Christopher Siyuan. « 3D Building Reconstruction Using 2D GANs ». Dans 2023 IEEE International Conference on Control, Electronics and Computer Technology (ICCECT). IEEE, 2023. http://dx.doi.org/10.1109/iccect57938.2023.10141185.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Vyakaranal, Shashidhara B., Akshata Hiremath, Inzamam Sayyed, Kshitij Ijari, S. M. Meena, Sunil V. Gurlahosur et Uday Kulkarni. « 2D Image Reconstruction using Differentiable Plasticity ». Dans 2021 6th International Conference for Convergence in Technology (I2CT). IEEE, 2021. http://dx.doi.org/10.1109/i2ct51068.2021.9418086.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Sediono, Wahju, et Andrian A. Lestari. « 2D Image reconstruction of radar INDERA ». Dans 2011 4th International Conference on Mechatronics (ICOM). IEEE, 2011. http://dx.doi.org/10.1109/icom.2011.5937155.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Yan, Hua, Hui Dou, Guannan Chen et Li Yao. « 3D temperature field reconstruction based on the interpolation of 2D acoustic reconstructions ». Dans Fifth International Conference on Machine Vision (ICMV 12), sous la direction de Yulin Wang, Liansheng Tan et Jianhong Zhou. SPIE, 2013. http://dx.doi.org/10.1117/12.2020948.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Jing Sun, She Shang et Jia-Dong Xu. « 3D shape reconstruction from 2D ISAR measurements ». Dans 2012 International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP). IEEE, 2012. http://dx.doi.org/10.1109/icwamtip.2012.6413431.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Kamencay, Patrik, Martina Zachariasova, Robert Hudec, Miroslav Benco et Roman Radil. « 3D image reconstruction from 2D CT slices ». Dans 2014 3DTV-Conference : The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON 2014). IEEE, 2014. http://dx.doi.org/10.1109/3dtv.2014.6874742.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Nous offrons des réductions sur tous les plans premium pour les auteurs dont les œuvres sont incluses dans des sélections littéraires thématiques. Contactez-nous pour obtenir un code promo unique!