This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Class-Specific Object Pose Estimation and Reconstruction Using 3D Part Geometry

Arun C. S. Kumar, András Bódis-Szomorú, Suchendra Bhandarkar, Mukta Prasad
ECCV 2016 Geometry Meets Deep Learning Workshop


We propose a novel approach for detecting and reconstructing class-specific objects from 2D images. Reconstruction and detection, despite major advances, are still wanting in performance. Hence, approaches that try to solve them jointly, so that one can be used to resolve the ambiguities of the other, especially while employing data-driven class-specific learning, are increasingly popular. In this paper, we learn a deformable, fine-grained, part-based model from real world, class-specific, image sequences, so that given a new image, we can simultaneously estimate the 3D shape, viewpoint and the subsequent 2D detection results. This is a step beyond existing approaches, which are usually limited to 3D CAD shapes, regression based pose estimation, template based deformation modelling etc. We employ Structure from Motion (SfM) and part based models in our learning process, and estimate a 3D deformable object instance and a projection matrix that explains the image information. We demonstrate our approach with high quality qualitative and quantitative results on our real world RealCar dataset, as well as the EPFL car dataset.

Link to publisher's page
  author = {Arun C. S. Kumar and András Bódis-Szomorú and Suchendra Bhandarkar and Mukta Prasad},
  title = {Class-Specific Object Pose Estimation and Reconstruction Using 3D Part Geometry},
  booktitle = {ECCV 2016 Geometry Meets Deep Learning Workshop},
  year = {2016},
  pages = {280--295},
  volume = {III},
  editor = {Gang Hua and Hervé Jégou},
  publisher = {Springer International Publishing},
  keywords = {}