Semantic Correspondence via 2D-3D-2D Cycle

Published in Preprint, 2020

Yang You, Chengkun Li, Yujing Lou, Zhoujun Cheng, Lizhuang Ma, Cewu Lu, Weiming Wang

arXiv / PDF / code / BibTeX

Abstract

Visual semantic correspondence is an important topic in computer vision and could help machine understand objects in our daily life. However, most previous methods directly train on correspondences in 2D images, which is end-to-end but loses plenty of information in 3D spaces. In this paper, we propose a new method on predicting semantic correspondences by leveraging it to 3D domain and then project corresponding 3D models back to 2D domain, with their semantic labels. Our method leverages the advantages in 3D vision and can explicitly reason about objects self-occlusion and visibility.

BibTeX

@article{you2020semantic,
  title     = {Semantic Correspondence via 2D-3D-2D Cycle},
  author    = {Yang You and Chengkun Li and Yujing Lou and Zhoujun Cheng and Lizhuang Ma and Cewu Lu and Weiming Wang},
  journal   = {arXiv preprint arXiv:2004.09061},
  year      = {2020},
  eprint    = {2004.09061},
  archivePrefix = {arXiv}
}

Recommended citation: You, Y., Li, C., Lou, Y., Cheng, Z., Ma, L., Lu, C., & Wang, W. (2020). Semantic Correspondence via 2D-3D-2D Cycle. arXiv preprint arXiv:2004.09061.