Discovering Relationships between Object Categories via Universal Canonical Maps

Autor: Natalia Neverova, David Novotny, Artsiom Sanakoyeu, Andrea Vedaldi, Patrick Labatut

Publikováno v: CVPR

We tackle the problem of learning the geometry of multiple categories of deformable objects jointly. Recent work has shown that it is possible to learn a unified dense pose predictor for several categories of related objects. However, training such m

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b4cd5a65d7e5cc7df7415dd389ca08e
https://doi.org/10.1109/cvpr46437.2021.00047

Low Bandwidth Video-Chat Compression using Deep Generative Models

Autor: Daniel Haziza, Thibault Peyronel, Peizhao Zhang, Maxime Oquab, Oran Gafni, Tao Xu, Patrick Labatut, Camille Couprie, Yana Hasson, Onur Celebi, Bobo Bose-Kolanu, Pierre Stock

Publikováno v: CVPR Workshops

To unlock video chat for hundreds of millions of people hindered by poor connectivity or unaffordable data costs, we propose to authentically reconstruct faces on the receiver's device using facial landmarks extracted at the sender's side and transmi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::57e17ee435fcc8a5dab3a35202f36fac
http://arxiv.org/abs/2012.00328

Robust piecewise-planar 3D reconstruction and completion from large-scale unstructured point data

Autor: Patrick Labatut, Anne-Laure Chauve, Jean-Philippe Pons

Publikováno v: Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on
CVPR 2010, Twenty-Third IEEE Computer Society Conference on Computer Vision and Pattern Recognition
CVPR 2010, Twenty-Third IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Jun 2010, San Francisco, United States. pp.1261-1268, ⟨10.1109/CVPR.2010.5539824⟩
CVPR

http://www.normalesup.org/~labatut/papers/cvpr2010-robust-piecewise-planar.pdf; International audience; In this paper, we present a novel method, the first to date to our knowledge, which is capable of directly and automatically producing a concise a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a001794eb3f4d4b82de9c60c991d25bf
https://hal-enpc.archives-ouvertes.fr/hal-00654408

Towards high-resolution large-scale multi-view stereo

Autor: Patrick Labatut, Vu Hoang Hiep, Renaud Keriven, Jean-Philippe Pons

Publikováno v: CVPR
Proceedings of Conference on Computer Vision and Pattern Recognition
CVPR, Jun 2009, Miami, United States. pp.1430-1437

International audience; Boosted by the Middlebury challenge, the precision of dense multi-view stereovision methods has increased drastically in the past few years. Yet, most methods, although they perform well on this benchmark, are still inapplicab

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7f77f0ca8692252c2dbd767f78b3abb0
https://doi.org/10.1109/cvpr.2009.5206617

Efficient Multi-View Reconstruction of Large-Scale Scenes using Interest Points, Delaunay Triangulation and Graph Cuts

Autor: Renaud Keriven, Jean-Philippe Pons, Patrick Labatut

Publikováno v: ICCV

We present a novel method to reconstruct the 3D shape of a scene from several calibrated images. Our motivation is that most existing multi-view stereovision approaches require some knowledge of the scene extent and often even of its approximate geom

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::5c9a685f18200efe803d549983e9ad7a
https://doi.org/10.1109/iccv.2007.4408892