Journal
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
Volume -, Issue -, Pages 4365-4374Publisher
IEEE COMPUTER SOC
DOI: 10.1109/CVPR.2019.00450
Keywords
-
Funding
- Israel Ministry of Science [3-14719]
- Technion Hiroshi Fujiwara Cyber Security Research Center
- Israel Cyber Bureau
- ERC [335491, 802554]
- MIUR of the Department of Computer Science of Sapienza University
- European Research Council (ERC) [335491] Funding Source: European Research Council (ERC)
Ask authors/readers for more resources
We introduce the first completely unsupervised correspondence learning approach for deformable 3D shapes. Key to our model is the understanding that natural deformations, such as changes in pose, approximately preserve the metric structure of the surface, yielding a natural criterion to drive the learning process toward distortion-minimizing predictions. On this basis, we overcome the need for annotated data and replace it by a purely geometric criterion. The resulting learning model is class-agnostic, and is able to leverage any type of deformable geometric data for the training phase. In contrast to existing supervised approaches which specialize on the class seen at training time, we demonstrate stronger generalization as well as applicability to a variety of challenging settings. We showcase our method on a wide selection of correspondence benchmarks, where the proposed method outperforms other methods in terms of accuracy, generalization, and efficiency.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available