Category-Level Pose Retrieval with Contrastive Features Learnt with Occlusion Augmentation. (arXiv:2208.06195v2 [cs.CV] UPDATED)

Pose estimation is usually tackled as either a bin classification problem or
as a regression problem. In both cases, the idea is to directly predict the
pose of an object. This is a non-trivial task because of appearance variations
of similar poses and similarities between different poses. Instead, we follow
the key idea that it is easier to compare two poses than to estimate them.
Render-and-compare approaches have been employed to that end, however, they
tend to be unstable, computationally …

arxiv augmentation cv features retrieval