Skip to Main content Skip to Navigation
Conference papers

Flexible Object Models for Category-Level 3D Object Recognition

Akash Kushal 1, 2 Cordelia Schmid 3 Jean Ponce 4, 5 
3 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
4 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique - ENS Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we propose a novel framework for visual object recognition where object classes are represented by assemblies of partial surface models (PSMs) obeying loose local geometric constraints. The PSMs themselves are formed of dense, locally rigid assemblies of image features. Since our model only enforces local geometric consistency, both at the level of model parts and at the level of individual features within the parts, it is robust to viewpoint changes and intra-class variability. The proposed approach has been implemented, and it outperforms the state-of-the-art algorithms for object detection and localization recently compared in [14] on the Pascal 2005 VOC Challenge Cars Test 1 data.
Document type :
Conference papers
Complete list of metadata

Cited literature [19 references]  Display  Hide  Download
Contributor : THOTH Team Connect in order to contact the contributor
Submitted on : Monday, December 20, 2010 - 10:28:57 AM
Last modification on : Thursday, March 17, 2022 - 10:08:39 AM
Long-term archiving on: : Monday, March 21, 2011 - 3:32:46 AM


Files produced by the author(s)




Akash Kushal, Cordelia Schmid, Jean Ponce. Flexible Object Models for Category-Level 3D Object Recognition. CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2007, Minneapolis, United States. pp.1-8, ⟨10.1109/CVPR.2007.383149⟩. ⟨inria-00548682⟩



Record views


Files downloads