Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapes
This addresses a fundamental challenge in computer vision for aligning complex 3D models, with broad applications in fields like graphics and robotics.
The paper tackles the problem of dense correspondence mapping between non-isometric deformable shapes without labels, achieving state-of-the-art results by a large margin across various tasks.
We present the first utterly self-supervised network for dense correspondence mapping between non-isometric shapes. The task of alignment in non-Euclidean domains is one of the most fundamental and crucial problems in computer vision. As 3D scanners can generate highly complex and dense models, the mission of finding dense mappings between those models is vital. The novelty of our solution is based on a cyclic mapping between metric spaces, where the distance between a pair of points should remain invariant after the full cycle. As the same learnable rules that generate the point-wise descriptors apply in both directions, the network learns invariant structures without any labels while coping with non-isometric deformations. We show here state-of-the-art-results by a large margin for a variety of tasks compared to known self-supervised and supervised methods.