Unsupervised Dense Shape Correspondence using Heat Kernels
Ayguen M, Laehner Z, Cremers D (2020)
Publication Type: Conference contribution
Publication year: 2020
Publisher: Institute of Electrical and Electronics Engineers Inc.
Pages Range: 573-582
Conference Proceedings Title: Proceedings - 2020 International Conference on 3D Vision, 3DV 2020
Event location: Virtual, Fukuoka, JPN
ISBN: 9781728181288
DOI: 10.1109/3DV50981.2020.00067
Abstract
In this work, we propose an unsupervised method for learning dense correspondences between shapes using a recent deep functional map framework. Instead of depending on ground-truth correspondences or the computationally expensive geodesic distances, we use heat kernels. These can be computed quickly during training as the supervisor signal. Moreover, we propose a curriculum learning strategy using different heat diffusion times which provide different levels of difficulty during optimization without any sampling mechanism or hard example mining. We present the results of our method on different benchmarks which have various challenges like partiality, topological noise and different connectivity.
Involved external institutions
Germany (DE)How to cite
APA:
Ayguen, M., Laehner, Z., & Cremers, D. (2020). Unsupervised Dense Shape Correspondence using Heat Kernels. In Proceedings - 2020 International Conference on 3D Vision, 3DV 2020 (pp. 573-582). Virtual, Fukuoka, JPN: Institute of Electrical and Electronics Engineers Inc..
MLA:
Ayguen, Mehmet, Zorah Laehner, and Daniel Cremers. "Unsupervised Dense Shape Correspondence using Heat Kernels." Proceedings of the 8th International Conference on 3D Vision, 3DV 2020, Virtual, Fukuoka, JPN Institute of Electrical and Electronics Engineers Inc., 2020. 573-582.
BibTeX: Download