Centre dedocumentation
scientifique

Complete 3D scene parsing from an RGBD image / Chuhang Zou in International journal of computer vision, vol 127 n° 2 (February 2019)  

Public [article]  inInternational journal of computer vision > vol 127 n° 2 (February 2019) . - pp 143 - 162 Titre : Complete 3D scene parsing from an RGBD image Type de document : Article/Communication Auteurs : Chuhang Zou, Auteur ; Ruiqi Guo, Auteur ; Zhizhong Li, Auteur ; Derek Hoiem, Auteur Année de publication : 2019 Article en page(s) : pp 143 - 162 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] cohérence géométrique [Termes descripteurs IGN] compréhension de l'image [Termes descripteurs IGN] image isolée [Termes descripteurs IGN] image RVB [Termes descripteurs IGN] reconstruction d'objet [Termes descripteurs IGN] scène 3D Résumé : (Auteur) One major goal of vision is to infer physical models of objects, surfaces, and their layout from sensors. In this paper, we aim to interpret indoor scenes from one RGBD image. Our representation encodes the layout of orthogonal walls and the extent of objects, modeled with CAD-like 3D shapes. We parse both the visible and occluded portions of the scene and all observable objects, producing a complete 3D parse. Such a scene interpretation is useful for robotics and visual reasoning, but difficult to produce due to the well-known challenge of segmentation, the high degree of occlusion, and the diversity of objects in indoor scenes. We take a data-driven approach, generating sets of potential object regions, matching to regions in training images, and transferring and aligning associated 3D models while encouraging fit to observations and spatial consistency. We use support inference to aid interpretation and propose a retrieval scheme that uses convolutional neural networks to classify regions and retrieve objects with similar shapes. We demonstrate the performance of our method on our newly annotated NYUd v2 dataset (Silberman et al., in: Computer vision-ECCV, 2012, pp 746–760, 2012) with detailed 3D shapes. Numéro de notice : A2018-598 Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-018-1133-z date de publication en ligne : 21/11/2018 En ligne : https://doi.org/10.1007/s11263-018-1133-z Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92525 [article]

Visibility estimation in point clouds with variable density / Pierre Biasutti (2019)    

Public Titre : Visibility estimation in point clouds with variable density Type de document : Article/Communication Auteurs : Pierre Biasutti, Auteur ; Aurélie Bugeau, Auteur ; Jean-François Aujol, Auteur ; Mathieu Brédif , Auteur Congrès : VISAPP 2019, 14th International Conference on Computer Vision Theory and Applications (25 février 2019; Prague, République tchèque), Commanditaire Editeur : [s.l.] : [s.n.] Année de publication : 2019 Projets : GOTMI / Papadakis, Nicolas Importance : 10 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] densité des points [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] reconstruction d'objet [Termes descripteurs IGN] semis de points [Termes descripteurs IGN] visibilité [Termes descripteurs IGN] voisinage (topologie) Résumé : (auteur) Estimating visibility in point clouds has many applications such as visualization, surface reconstruction and scene analysis through fusion of LiDAR point clouds and images. However, most current works rely on methods that require strong assumptions on the point cloud density, which are not valid for LiDAR point clouds acquired from mobile mapping systems, leading to low quality of point visibility estimations. This work presents a novel approach for the estimation of the visibility of a point cloud from a viewpoint. The method is designed to be fully automatic and it makes no assumption on the point cloud density. The visibility of each point is estimated by considering its screen-space neighborhood from the given viewpoint. Our results show that our approach succeeds better in estimating the visibility on real-world data acquired using LiDAR scanners. We evaluate our approach by comparing its results to a new manually annotated dataset, which we make available online. Numéro de notice : C2019-007 Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl affiliation_auteur_principal : 3102 affiliation_auteur_2 : 3102 affiliation_auteur_3 : 27730 affiliation_auteur_4 : 536752 En ligne : https://hal.archives-ouvertes.fr/hal-01812061v2 Format de la ressource électronique : lien vers HAL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92633

Documents numériques

en open access Visibility estimation in point clouds with variable density - version HAL URL

Surface reconstruction of incomplete datasets: A novel Poisson surface approach based on CSRBF / Jules Morel in Computers and graphics, vol 74 (August 2018)  

Public [article]  inComputers and graphics > vol 74 (August 2018) . - pp 44 - 55 Titre : Surface reconstruction of incomplete datasets: A novel Poisson surface approach based on CSRBF Type de document : Article/Communication Auteurs : Jules Morel, Auteur ; Alexandra Bac, Auteur ; Cédric Vega , Auteur Année de publication : 2018 Projets : DIABOLO / Packalen, Tuula Article en page(s) : pp 44 - 55 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] approximation [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] équation de Poisson [Termes descripteurs IGN] fonction de base radiale [Termes descripteurs IGN] jeu de données localisées [Termes descripteurs IGN] reconstruction d'objet Résumé : (auteur) This paper introduces a novel surface reconstruction method based on unorganized point clouds, which focuses on offering complete and closed mesh models of partially sampled object surfaces. To accomplish this task, our approach builds upon a known a priori model that coarsely describes the scanned object to guide the modeling of the shape based on heavily occluded point clouds. In the region of space visible to the scanner, we retrieve the surface by following the resolution of a Poisson problem: the surface is modeled as the zero level-set of an implicit function whose gradient is the closest to the vector field induced by the 3D sample normals. In the occluded region of space, we consider the a priori model as a sufficiently accurate descriptor of the shape. Both models, which are expressed in the same basis of compactly supported radial functions to ensure computation and memory efficiency, are then blended to obtain a closed model of the scanned object. Our method is finally tested on traditional testing datasets to assess its accuracy and on simulated terrestrial LiDAR scanning (TLS) point clouds of trees to assess its ability to handle complex shapes with occlusions. Numéro de notice : A2018-530 Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.cag.2018.05.004 date de publication en ligne : 17/05/2018 En ligne : https://doi.org/10.1016/j.cag.2018.05.004 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91400 [article]

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 descripteurs IGN] contrainte géométrique [Termes descripteurs IGN] estimation de pose [Termes descripteurs IGN] image RVB [Termes descripteurs IGN] Kinect [Termes descripteurs IGN] méthode de réduction d'énergie [Termes descripteurs IGN] optimisation (mathématiques) [Termes descripteurs IGN] reconstruction d'objet [Termes descripteurs 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 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]

Large scale textured mesh reconstruction from mobile mapping images and LIDAR scans / Mohamed Boussaha in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, IV-2 ([28/05/2018])  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > IV-2 [28/05/2018] . - pp 49 - 56 Titre : Large scale textured mesh reconstruction from mobile mapping images and LIDAR scans Type de document : Article/Communication Auteurs : Mohamed Boussaha, Auteur ; Bruno Vallet , Auteur ; Patrick Rives, Auteur Congrès : ISPRS 2018, TC II Mid-term Symposium "Towards Photogrammetry 2020" (4 - 7 juin 2018; Riva del Garda, Italie) , Commanditaire Année de publication : 2018 Projets : PLaTINUM / Gouet-Brunet, Valérie Article en page(s) : pp 49 - 56 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes descripteurs IGN] architecture pipeline [Termes descripteurs IGN] chaîne de traitement [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] grande échelle [Termes descripteurs IGN] maillage [Termes descripteurs IGN] orthoimage [Termes descripteurs IGN] reconstruction d'objet [Termes descripteurs IGN] Rouen [Termes descripteurs IGN] texture d'image Résumé : (auteur) The representation of 3D geometric and photometric information of the real world is one of the most challenging and extensively studied research topics in the photogrammetry and robotics communities. In this paper, we present a fully automatic framework for 3D high quality large scale urban texture mapping using oriented images and LiDAR scans acquired by a terrestrial Mobile Mapping System (MMS). First, the acquired points and images are sliced into temporal chunks ensuring a reasonable size and time consistency between geometry (points) and photometry (images). Then, a simple, fast and scalable 3D surface reconstruction relying on the sensor space topology is performed on each chunk after an isotropic sampling of the point cloud obtained from the raw LiDAR scans. Finally, the algorithm proposed in (Waechter et al., 2014) is adapted to texture the reconstructed surface with the images acquired simultaneously, ensuring a high quality texture with no seams and global color adjustment. We evaluate our full pipeline on a dataset of 17 km of acquisition in Rouen, France resulting in nearly 2 billion points and 40000 full HD images. We are able to reconstruct and texture the whole acquisition in less than 30 computing hours, the entire process being highly parallel as each chunk can be processed independently in a separate thread or computer. Numéro de notice : A2018-329 Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.5194/isprs-annals-IV-2-49-2018 date de publication en ligne : 28/05/2018 En ligne : http://dx.doi.org/10.5194/isprs-annals-IV-2-49-2018 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90471 [article]

On the production of semantic and textured 3D meshes of large scale urban environments from mobile mapping images and LIDAR scans / Mohamed Boussaha (2018)    

Permalink

Algebraic method to speed up robust algorithms: example of laser-scanned point clouds / B. Palancz in Survey review, vol 49 n° 357 (December 2017)  

Permalink

Global, dense multiscale reconstruction for a billion points / Benjamin Ummenhofer in International journal of computer vision, vol 125 n° 1-3 (December 2017)  

Permalink

Bayesian graph-cut optimization for wall surfaces reconstruction in indoor environments / Georgios-Tsampikos Michailidis in The Visual Computer, vol 33 n° 10 (October 2017)  

Permalink

Multi-view performance capture of surface details / Nadia Robertini in International journal of computer vision, vol 124 n° 1 (August 2017)  

Permalink

Efficient edge-aware surface mesh reconstruction for urban scenes / András Bódis-Szomorú in Computer Vision and image understanding, vol 157 (April 2017)  

Permalink

Generalizing the prediction sum of squares statistic and formula, application to linear fractional image warp and surface fitting / Adrien Bartoli in International journal of computer vision, vol 122 n° 1 (March 2017)  

Permalink

Handbook on advances in remote sensing and geographic information systems / Margarita N. Favorskaya (2017)

Permalink

Generative models for road network reconstruction / Colin Kuntzsch in International journal of geographical information science IJGIS, vol 30 n° 5-6 (May - June 2016)  

Permalink

3D watertight mesh generation with uncertainties from ubiquitous data / Laurent Caraffa (2016)  

Permalink