Centre de documentation
scientifique

DiffusionNet: discretization agnostic learning on surfaces / Nicholas Sharp in ACM Transactions on Graphics, TOG, Vol 41 n° 3 (June 2022)  

Public [article]  inACM Transactions on Graphics, TOG > Vol 41 n° 3 (June 2022) . - pp 1 - 16 Titre : DiffusionNet: discretization agnostic learning on surfaces Type de document : Article/Communication Auteurs : Nicholas Sharp, Auteur ; Souhaib Attaiki, Auteur ; K. Crane, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 1 - 16 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle [Termes IGN] apprentissage profond [Termes IGN] discrétisation [Termes IGN] maillage [Termes IGN] Perceptron multicouche [Termes IGN] semis de points [Termes IGN] Triangular Regular Network [Termes IGN] voisinage (relation topologique) Résumé : (auteur) We introduce a new general-purpose approach to deep learning on three-dimensional surfaces based on the insight that a simple diffusion layer is highly effective for spatial communication. The resulting networks are automatically robust to changes in resolution and sampling of a surface—a basic property that is crucial for practical applications. Our networks can be discretized on various geometric representations, such as triangle meshes or point clouds, and can even be trained on one representation and then applied to another. We optimize the spatial support of diffusion as a continuous network parameter ranging from purely local to totally global, removing the burden of manually choosing neighborhood sizes. The only other ingredients in the method are a multi-layer perceptron applied independently at each point and spatial gradient features to support directional filters. The resulting networks are simple, robust, and efficient. Here, we focus primarily on triangle mesh surfaces and demonstrate state-of-the-art results for a variety of tasks, including surface classification, segmentation, and non-rigid correspondence. Numéro de notice : A2022-321 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1145/3507905 Date de publication en ligne : 07/03/2022 En ligne : https://doi.org/10.1145/3507905 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100369 [article]

City3D: Large-scale building reconstruction from airborne LiDAR point clouds / Jin Huang in Remote sensing, vol 14 n° 9 (May-1 2022)  

Public [article]  inRemote sensing > vol 14 n° 9 (May-1 2022) . - n° 2254 Titre : City3D: Large-scale building reconstruction from airborne LiDAR point clouds Type de document : Article/Communication Auteurs : Jin Huang, Auteur ; Jantien E. Stoter, Auteur ; Ravi Peters, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 2254 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] empreinte [Termes IGN] mur [Termes IGN] polygonale [Termes IGN] primitive géométrique [Termes IGN] reconstruction 3D du bâti [Termes IGN] semis de points [Termes IGN] toit [Termes IGN] Triangular Regular Network [Termes IGN] triangulation de Delaunay Résumé : (auteur) We present a fully automatic approach for reconstructing compact 3D building models from large-scale airborne point clouds. A major challenge of urban reconstruction from airborne LiDAR point clouds lies in that the vertical walls are typically missing. Based on the observation that urban buildings typically consist of planar roofs connected with vertical walls to the ground, we propose an approach to infer the vertical walls directly from the data. With the planar segments of both roofs and walls, we hypothesize the faces of the building surface, and the final model is obtained by using an extended hypothesis-and-selection-based polygonal surface reconstruction framework. Specifically, we introduce a new energy term to encourage roof preferences and two additional hard constraints into the optimization step to ensure correct topology and enhance detail recovery. Experiments on various large-scale airborne LiDAR point clouds have demonstrated that the method is superior to the state-of-the-art methods in terms of reconstruction accuracy and robustness. In addition, we have generated a new dataset with our method consisting of the point clouds and 3D models of 20k real-world buildings. We believe this dataset can stimulate research in urban reconstruction from airborne LiDAR point clouds and the use of 3D city models in urban applications. Numéro de notice : A2022-387 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/IMAGERIE Nature : Article DOI : 10.3390/rs14092254 Date de publication en ligne : 07/05/2022 En ligne : https://doi.org/10.3390/rs14092254 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100667 [article]

Optimal routefinding with unlimited possible directions of movement / Denis J. Dean in Transactions in GIS, vol 15 n° 1 (February 2011)  

Public [article]  inTransactions in GIS > vol 15 n° 1 (February 2011) . - pp 87 - 107 Titre : Optimal routefinding with unlimited possible directions of movement Type de document : Article/Communication Auteurs : Denis J. Dean, Auteur Année de publication : 2011 Article en page(s) : pp 87 - 107 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes IGN] base de données localisées [Termes IGN] calcul d'itinéraire [Termes IGN] données maillées [Termes IGN] recherche du chemin optimal, algorithme de [Termes IGN] réseau routier [Termes IGN] système d'information géographique [Termes IGN] Triangular Regular Network Résumé : (Auteur) Finding optimal paths through raster databases is limited by the very nature of the raster data itself. This limitation restricts the possible directions of movement through the database from the infinite possibilities found in the real world to a finite number of possibilities defined by the cell-to-cell movement that characterizes raster databases. A Triangulated Irregular Network (TIN)-based alternative optimization model that allows unlimited possible directions of movement is presented. While not without its own limitations, this new approach offers a viable alternative to raster-based optimal routefinding. Numéro de notice : A2011-059 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/j.1467-9671.2010.01244.x Date de publication en ligne : 16/02/2011 En ligne : https://doi.org/10.1111/j.1467-9671.2010.01244.x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=30840 [article]

Obtaining high fidelity triangular Regular Network from only DEM points / T. Gökgöz in Cartographic journal (the), vol 47 n° 2 (May 2010)  

Public [article]  inCartographic journal (the) > vol 47 n° 2 (May 2010) . - pp 150 - 156 Titre : Obtaining high fidelity triangular Regular Network from only DEM points Type de document : Article/Communication Auteurs : T. Gökgöz, Auteur Année de publication : 2010 Article en page(s) : pp 150 - 156 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] contour [Termes IGN] interpolation [Termes IGN] modèle numérique de surface [Termes IGN] pente [Termes IGN] tessellation [Termes IGN] Triangular Regular Network [Termes IGN] triangulation (topologie) Résumé : (Auteur) When the source data for the digital elevation model (DEM) are not known and any additional information or features such as skeleton lines of terrain is not available, a triangular regular network (TRN) is constructed with simple subdivision using one or two diagonals uniformly. Such a model gives inaccurate directions for interpolation because of the inaccurate diagonals used in triangulation and thereby, results in inaccurate contours representing artificial terrain features. In this study, a new method is developed based on slope information computed at DEM points determining accurate diagonals in the subdivision process, which is beneficial not only through the skeleton lines of a terrain but also all over the DEM. Consequently, it is shown that the proposed method is able to build a high fidelity TRN from a DEM without any additional information or features. Copyright British Cartographic Society Numéro de notice : A2010-260 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1179/000870409X12584524219009 Date de publication en ligne : 18/07/2013 En ligne : https://doi.org/10.1179/000870409X12584524219009 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=30454 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
030-2010021	RAB	Revue	Centre de documentation	En réserve L003	Disponible