Descripteur
Documents disponibles dans cette catégorie (9)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Titre : Learning 3D generation and matching Type de document : Thèse/HDR Auteurs : Thibault Groueix, Auteur ; Mathieu Aubry, Directeur de thèse Editeur : Paris : Ecole Nationale des Ponts et Chaussées ENPC Année de publication : 2020 Importance : 169 p. Format : 21 x 30 cm Note générale : bibliographie
A doctoral thesis in the domain of automated signal and image processing submitted to École Doctorale Paris-Est
Mathématiques et Sciences et Technologies de l’Information et de la CommunicationLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] appariement de formes
[Termes IGN] appariement dense
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] déformation de surface
[Termes IGN] isométrie
[Termes IGN] maillage
[Termes IGN] modélisation 3D
[Termes IGN] reconstruction 3D
[Termes IGN] reconstruction d'image
[Termes IGN] segmentation d'image
[Termes IGN] semis de points
[Termes IGN] voxelIndex. décimale : THESE Thèses et HDR Résumé : (auteur) The goal of this thesis is to develop deep learning approaches to model and analyse 3D shapes. Progress in this field could democratize artistic creation of 3D assets which currently requires time and expert skills with technical software. We focus on the design of deep learning solutions for two particular tasks, key to many 3D modeling applications: single-view reconstruction and shape matching. A single-view reconstruction (SVR) method takes as input a single image and predicts the physical world which produced that image. SVR dates back to the early days of computer vision. In particular, in the 1960s, Lawrence G. Roberts proposed to align simple 3D primitives to the input image under the assumption that the physical world is made of cuboids. Another approach proposed by Berthold Horn in the 1970s is to decompose the input image in intrinsic images and use those to predict the depth of every input pixel. Since several configurations of shapes, texture and illumination can explain the same image, both approaches need to form assumptions on the distribution of images and 3D shapes to resolve the ambiguity. In this thesis, we learn these assumptions from large-scale datasets instead of manually designing them. Learning allows us to perform complete object reconstruction, including parts which are not visible in the input image. Shape matching aims at finding correspondences between 3D objects. Solving this task requires both a local and global understanding of 3D shapes which is hard to achieve explicitly. Instead we train neural networks on large-scale datasets to solve this task and capture this knowledge implicitly through their internal parameters.Shape matching supports many 3D modeling applications such as attribute transfer, automatic rigging for animation, or mesh editing.The first technical contribution of this thesis is a new parametric representation of 3D surfaces modeled by neural networks.The choice of data representation is a critical aspect of any 3D reconstruction algorithm. Until recently, most of the approaches in deep 3D model generation were predicting volumetric voxel grids or point clouds, which are discrete representations. Instead, we present an alternative approach that predicts a parametric surface deformation ie a mapping from a template to a target geometry. To demonstrate the benefits of such a representation, we train a deep encoder-decoder for single-view reconstruction using our new representation. Our approach, dubbed AtlasNet, is the first deep single-view reconstruction approach able to reconstruct meshes from images without relying on an independent post-processing, and can do it at arbitrary resolution without memory issues. A more detailed analysis of AtlasNet reveals it also generalizes better to categories it has not been trained on than other deep 3D generation approaches.Our second main contribution is a novel shape matching approach purely based on reconstruction via deformations. We show that the quality of the shape reconstructions is critical to obtain good correspondences, and therefore introduce a test-time optimization scheme to refine the learned deformations. For humans and other deformable shape categories deviating by a near-isometry, our approach can leverage a shape template and isometric regularization of the surface deformations. As category exhibiting non-isometric variations, such as chairs, do not have a clear template, we learn how to deform any shape into any other and leverage cycle-consistency constraints to learn meaningful correspondences. Our reconstruction-for-matching strategy operates directly on point clouds, is robust to many types of perturbations, and outperforms the state of the art by 15% on dense matching of real human scans. Note de contenu : 1- Introduction
2 Related Work
3 AtlasNet: A Papier-Mache Approach to Learning 3D Surface Generation
4 3D-CODED : 3D Correspondences by Deep Deformation
5 Unsupervised cycle-consistent deformation for shape matching
6 ConclusionNuméro de notice : 28310 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Automated signal and image processing : Paris-Est : 2020 Organisme de stage : LIGM DOI : sans En ligne : https://tel.archives-ouvertes.fr/tel-03127055v2/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98201 Embedding road networks and travel time into distance metrics for urban modelling / Henry Crosby in International journal of geographical information science IJGIS, Vol 33 n° 3-4 (March - April 2019)
[article]
Titre : Embedding road networks and travel time into distance metrics for urban modelling Type de document : Article/Communication Auteurs : Henry Crosby, Auteur ; theodore Damoulas, Auteur ; Stephen A. Jarvis, Auteur Année de publication : 2019 Article en page(s) : pp 512 - 536 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale
[Termes IGN] covariance
[Termes IGN] distance euclidienne
[Termes IGN] durée de trajet
[Termes IGN] espace-temps
[Termes IGN] géostatistique
[Termes IGN] isométrie
[Termes IGN] krigeage
[Termes IGN] logement
[Termes IGN] modèle de simulation
[Termes IGN] réseau routier
[Termes IGN] trafic routier
[Termes IGN] urbanisme
[Termes IGN] variogrammeRésumé : (auteur) Urban environments are restricted by various physical, regulatory and customary barriers such as buildings, one-way systems and pedestrian crossings. These features create challenges for predictive modelling in urban space, as most proximity-based models rely on Euclidean (straight line) distance metrics which, given restrictions within the urban landscape, do not fully capture spatial urban processes. Here, we argue that road distance and travel time provide effective alternatives, and we develop a new low-dimensional Euclidean distance metric based on these distances using an isomap approach. The purpose of this is to produce a valid covariance matrix for Kriging. Our primary methodological contribution is the derivation of two symmetric dissimilarity matrices (B+ and B2+), with which it is possible to compute low-dimensional Euclidean metrics for the production of a positive definite covariance matrix with commonly utilised kernels. This new method is implemented into a Kriging predictor to estimate house prices on 3,669 properties in Coventry, UK. We find that a metric estimating a combination of road distance and travel time, in both R2 and R3, produces a superior house price predictor compared with alternative state-of-the-art methods, that is, a standard Euclidean metric in RN and a non-restricted road distance metric in R2 and R3. F Numéro de notice : A2019-024 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2018.1547386 Date de publication en ligne : 06/12/2018 En ligne : https://doi.org/10.1080/13658816.2018.1547386 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91952
in International journal of geographical information science IJGIS > Vol 33 n° 3-4 (March - April 2019) . - pp 512 - 536[article]Réservation
Réserver ce documentExemplaires (2)
Code-barres Cote Support Localisation Section Disponibilité 079-2019031 RAB Revue Centre de documentation En réserve L003 Disponible 079-2019032 RAB Revue Centre de documentation En réserve L003 Disponible Non-rigid registration of 3D point clouds under isometric deformation / Xuming Ge in ISPRS Journal of photogrammetry and remote sensing, vol 121 (November 2016)
[article]
Titre : Non-rigid registration of 3D point clouds under isometric deformation Type de document : Article/Communication Auteurs : Xuming Ge, Auteur Année de publication : 2016 Article en page(s) : pp 192 – 202 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] alignement
[Termes IGN] déformation géométrique
[Termes IGN] image 3D
[Termes IGN] isométrie
[Termes IGN] semis de pointsRésumé : (Auteur) An algorithm for pairwise non-rigid registration of 3D point clouds is presented in the specific context of isometric deformations. The critical step is registration of point clouds at different epochs captured from an isometric deformation surface within overlapping regions. Based on characteristics invariant under isometric deformation, a variant of the four-point congruent sets algorithm is applied to generate correspondences between two deformed point clouds, and subsequently a RANSAC framework is used to complete cluster extraction in preparation for global optimal alignment. Examples are presented and the results compared with existing approaches to demonstrate the two main contributions of the technique: a success rate for generating true correspondences of 90% and a root mean square error after final registration of 2–3 mm. Numéro de notice : A2016--018 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.09.009 En ligne : https://doi.org/10.1016/j.isprsjprs.2016.09.009 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83880
in ISPRS Journal of photogrammetry and remote sensing > vol 121 (November 2016) . - pp 192 – 202[article]Mathématiques, enseignement de spécialité terminale TS programme 1994 / G. Bontemps (1994)
Titre : Mathématiques, enseignement de spécialité terminale TS programme 1994 Type de document : Guide/Manuel Auteurs : G. Bontemps, Auteur ; H. Carnec, Auteur ; G. Haye, Auteur ; M. Nouet, Auteur ; R. Seroux, Auteur ; E. Serra, Auteur ; J. Venard, Auteur Editeur : Paris : Bordas Année de publication : 1994 Importance : 176 p. Format : 20 x 27 cm ISBN/ISSN/EAN : 978-2-04-020993-3 Langues : Français (fre) Descripteur : [Vedettes matières IGN] Mathématique
[Termes IGN] analyse vectorielle
[Termes IGN] formation
[Termes IGN] isométrie
[Termes IGN] nombre complexe
[Termes IGN] similitudeNuméro de notice : 64190 Affiliation des auteurs : non IGN Thématique : MATHEMATIQUE Nature : Manuel de cours Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=48969 Réservation
Réserver ce documentExemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 64190-01 23.00 Livre Centre de documentation Mathématiques Disponible Notions sur les représentations planes de la Terre / Gilbert Gambier (1984)
Titre : Notions sur les représentations planes de la Terre Type de document : Guide/Manuel Auteurs : Gilbert Gambier, Auteur Editeur : Paris : Institut Géographique National - IGN (1940-2007) Année de publication : 1984 Importance : 115 p. Format : 21 x 30 cm Langues : Français (fre) Descripteur : [Vedettes matières IGN] Projections
[Termes IGN] angle
[Termes IGN] Bartholomew, John Georges
[Termes IGN] Clairaut, Alexis
[Termes IGN] Déformation
[Termes IGN] isométrie
[Termes IGN] Laplace, Pierre Simon de
[Termes IGN] latitude
[Termes IGN] longitude
[Termes IGN] navigation
[Termes IGN] projection (équivalente) de Mollweide
[Termes IGN] projection Aitoff
[Termes IGN] projection azimutale
[Termes IGN] projection de Dalby
[Termes IGN] projection de Lorgna
[Termes IGN] projection équivalente
[Termes IGN] projection sinusoïdale
[Termes IGN] projection stéréographique
[Termes IGN] sphèreIndex. décimale : 30.20 Projections - généralités Numéro de notice : 47983 Affiliation des auteurs : IGN (1940-2011) Thématique : GEOMATIQUE/POSITIONNEMENT Nature : Manuel de cours IGN Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=47937 Réservation
Réserver ce documentExemplaires (3)
Code-barres Cote Support Localisation Section Disponibilité 47983-01 30.20 Livre Centre de documentation Géodésie Disponible 47983-02 30.20 Livre Centre de documentation Géodésie Disponible 47983-03 K321 Livre LASTIG Dépôt en unité Exclu du prêt Quelques problèmes de rotation dans l'espace : applications en géodesie, en dynamique des solides et en planètologie / Georges Balmino (1978)PermalinkNotions sur les représentations planes de la Terre / Gilbert Gambier (1975)PermalinkLeçons sur les projections des cartes géographiques / Albert Reyt (1967)PermalinkLeçons sur les projections des cartes géographiques / Albert Reyt (1960)Permalink