Learning 3D Representations of Dynamic Environments from a Single Camera

Authors

Gengshan Yang, Minh Vo, Neverova Natalia, Deva Ramanan, Andrea Vedaldi, Christopher Choy

CVPR, 2021

Abstract

Learning 3D representations of dynamic environments from a single camera presents substantial challenges due to the inherent ambiguities in monocular observations. This paper introduces novel approaches for reconstructing dynamic 3D scenes using advanced neural representations and temporal consistency.

• blog
• paper
• code

Bibtex

@article{lan2021discobox,
  title={DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision},
  author={Lan, Shiyi and Yu, Zhiding and Choy, Christopher and Radhakrishnan, Subhashree and Liu, Guilin and Zhu, Yuke and Davis, Larry S and Anandkumar, Anima},
  journal={arXiv preprint arXiv:2105.06464},
  year={2021}
}