The goal of this paper is to learn dense 3D shape correspondence for topologyvarying objects in an unsupervised manner. Conventional implicit functions estimate the occupancy of a 3D point given a shape latent code. Instead, our novel implicit function produces a part embedding vector for each 3D point, which is assumed to be similar to its densely corresponded point in another 3D shape of the same object category. Furthermore, we implement dense correspondence through an inverse function mapping from the part embedding to a corresponded 3D point. Both functions are jointly learned with several effective loss functions to realize our assumption, together with the encoder generating the shape latent code. During inference, if a user selects an arbitrary point on the source shape, our algorithm can automatically generate a confidence score indicating whether there is a correspondence on the target shape, as well as the corresponding semantic point if there is one. Such a mechanism inherently benefits manmade objects with different part constitutions. The effectiveness of our approach is demonstrated through unsupervised 3D semantic correspondence and shape segmentation.
Learning Implicit Functions for TopologyVarying Dense 3D Shape Correspondence
Feng Liu, Xiaoming LiuKeywords: 3D Shape Correspondence, Semantic Segmentation
Implicit Dense Correspondence Source Code
The source code can be downloaded from here.
Publications

Learning Implicit Functions for TopologyVarying Dense 3D Shape Correspondence
Feng Liu, Xiaoming Liu
In Proceeding of 2020 Conference on Neural Information Processing Systems (NeurIPS 2020), Virtual, Dec. 2020 (Oral)
Bibtex  PDF  arXiv  Supplemental  Poster  Code  Video