Centre de documentation
scientifique

SDF-2-SDF registration for real-time 3D reconstruction from RGB-D data / Miroslava Slavcheva in International journal of computer vision, vol 126 n° 6 (June 2018)  

Public [article]  inInternational journal of computer vision > vol 126 n° 6 (June 2018) . - pp 615 - 636 Titre : SDF-2-SDF registration for real-time 3D reconstruction from RGB-D data Type de document : Article/Communication Auteurs : Miroslava Slavcheva, Auteur ; Wadim Kehl, Auteur ; Nassir Navab, Auteur ; Slobodan Ilic, Auteur Année de publication : 2018 Article en page(s) : pp 615 - 636 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] contrainte géométrique [Termes IGN] estimation de pose [Termes IGN] image RVB [Termes IGN] Kinect [Termes IGN] méthode de réduction d'énergie [Termes IGN] optimisation (mathématiques) [Termes IGN] reconstruction d'objet [Termes IGN] semis de points [Termes IGN] voxel Mots-clés libres : simultaneous localization and mapping (SLAM) Résumé : (Auteur) We tackle the task of dense 3D reconstruction from RGB-D data. Contrary to the majority of existing methods, we focus not only on trajectory estimation accuracy, but also on reconstruction precision. The key technique is SDF-2-SDF registration, which is a correspondence-free, symmetric, dense energy minimization method, performed via the direct voxel-wise difference between a pair of signed distance fields. It has a wider convergence basin than traditional point cloud registration and cloud-to-volume alignment techniques. Furthermore, its formulation allows for straightforward incorporation of photometric and additional geometric constraints. We employ SDF-2-SDF registration in two applications. First, we perform small-to-medium scale object reconstruction entirely on the CPU. To this end, the camera is tracked frame-to-frame in real time. Then, the initial pose estimates are refined globally in a lightweight optimization framework, which does not involve a pose graph. We combine these procedures into our second, fully real-time application for larger-scale object reconstruction and SLAM. It is implemented as a hybrid system, whereby tracking is done on the GPU, while refinement runs concurrently over batches on the CPU. To bound memory and runtime footprints, registration is done over a fixed number of limited-extent volumes, anchored at geometry-rich locations. Extensive qualitative and quantitative evaluation of both trajectory accuracy and model fidelity on several public RGB-D datasets, acquired with various quality sensors, demonstrates higher precision than related techniques. Numéro de notice : A2018-410 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-017-1057-z Date de publication en ligne : 18/12/2017 En ligne : https://doi.org/10.1007/s11263-017-1057-z Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90884 [article]

Real-time accurate 3D head tracking and pose estimation with consumer RGB-D cameras / David Joseph Tan in International journal of computer vision, vol 126 n° 2-4 (April 2018)  

Public [article]  inInternational journal of computer vision > vol 126 n° 2-4 (April 2018) . - pp 158 - 183 Titre : Real-time accurate 3D head tracking and pose estimation with consumer RGB-D cameras Type de document : Article/Communication Auteurs : David Joseph Tan, Auteur ; Federico Tombari, Auteur ; Nassir Navab, Auteur Année de publication : 2018 Article en page(s) : pp 158 - 183 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] détection de visage [Termes IGN] données localisées 3D [Termes IGN] estimation de pose [Termes IGN] image RVB [Termes IGN] méthode robuste [Termes IGN] séquence d'images [Termes IGN] temps réel Résumé : (Auteur) We demonstrate how 3D head tracking and pose estimation can be effectively and efficiently achieved from noisy RGB-D sequences. Our proposal leverages on a random forest framework, designed to regress the 3D head pose at every frame in a temporal tracking manner. One peculiarity of the algorithm is that it exploits together (1) a generic training dataset of 3D head models, which is learned once offline; and, (2) an online refinement with subject-specific 3D data, which aims for the tracker to withstand slight facial deformations and to adapt its forest to the specific characteristics of an individual subject. The combination of these works allows our algorithm to be robust even under extreme poses, where the user’s face is no longer visible on the image. Finally, we also propose another solution that utilizes a multi-camera system such that the data simultaneously acquired from multiple RGB-D sensors helps the tracker to handle challenging conditions that affect a subset of the cameras. Notably, the proposed multi-camera frameworks yields a real-time performance of approximately 8 ms per frame given six cameras and one CPU core, and scales up linearly to 30 fps with 25 cameras. Numéro de notice : A2018-406 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-017-0988-8 Date de publication en ligne : 02/02/2017 En ligne : https://doi.org/10.1007/s11263-017-0988-8 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90879 [article]