Unsupervised learning of object frames by dense equivariant image labelling

@inproceedings{Thewlis2017UnsupervisedLO,
  title={Unsupervised learning of object frames by dense equivariant image labelling},
  author={James Thewlis and Hakan Bilen and Andrea Vedaldi},
  booktitle={NIPS},
  year={2017}
}
One of the key challenges of visual perception is to extract abstract models of 3D objects and object categories from visual measurements, which are affected by complex nuisance factors such as viewpoint, occlusion, motion, and deformations. Starting from the recent idea of viewpoint factorization, we propose a new approach that, given a large number of images of an object and no other supervision, can extract a dense object-centric coordinate frame. This coordinate frame is invariant to… CONTINUE READING
Related Discussions
This paper has been referenced on Twitter 33 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-7 of 7 extracted citations

Self-Supervised Learning of Geometrically Stable Features Through Probabilistic Introspection

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition • 2018
View 9 Excerpts
Method Support
Highly Influenced

Unsupervised Discovery of Object Landmarks as Structural Representations

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition • 2018
View 2 Excerpts