Building Part-based Object Detectors via 3D Geometry

Abhinav Shrivastava and Abhinav Gupta
International Conference on Computer Vision (ICCV), December, 2013.

  • Adobe portable document format (pdf) (4MB)
Copyright notice: 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. These works may not be reposted without the explicit permission of the copyright holder.

This paper proposes a novel part-based representation for modeling object categories. Our representation combines the effectiveness of deformable part-based models with the richness of geometric representation by defining parts based on consistent underlying 3D geometry. Our key hypothesis is that while the appearance and the arrangement of parts might vary across the instances of object categories, the constituent parts will still have consistent underlying 3D geometry. We propose to learn this geometry-driven deformable part-based model (gDPM) from a set of labeled RGBD images. We also demonstrate how the geometric representation of gDPM can help us leverage depth data during training and constrain the latent model learning problem. But most importantly, a joint geometric and appearance based representation not only allows us to achieve state-of-the-art results on object detection but also allows us to tackle the grand challenge of understanding 3D objects from 2D images.


Text Reference
Abhinav Shrivastava and Abhinav Gupta, "Building Part-based Object Detectors via 3D Geometry ," International Conference on Computer Vision (ICCV), December, 2013.

BibTeX Reference
   author = "Abhinav Shrivastava and Abhinav Gupta",
   title = "Building Part-based Object Detectors via 3D Geometry ",
   booktitle = "International Conference on Computer Vision (ICCV)",
   month = "December",
   year = "2013",