DPFM: Deep Partial Functional Maps

Abstract

We consider the problem of computing dense correspondences between non-rigid shapes with potentially significant partiality. Existing formulations tackle this problem through heavy manifold optimization in the spectral domain, given hand-crafted shape descriptors. In this paper, we propose the first learning method aimed directly at partial non-rigid shape correspondence. Our approach uses the functional map framework, can be trained in a supervised or unsupervised manner, and learns descriptors directly from the data, thus both improving robustness and accuracy in challenging cases. Furthermore, unlike existing techniques, our method is also applicable to partial-to-partial non-rigid matching, in which the common regions on both shapes are unknown a priori. We demonstrate that the resulting method is data-efficient, and achieves state-of-the-art results on several benchmark datasets. Our code and data can be found online: https://github.com/pvnieo/DPFM

References in corpus (11)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Geometric deep learning: going beyond Euclidean data
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Activation Functions: Comparison of trends in Practice and Research for Deep Learning
• Building Statistical Shape Spaces for 3D Human Modeling
• PRNet: Self-Supervised Learning for Partial-to-Partial Registration
• PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
• Non-Rigid Puzzles
• CNNs on Surfaces using Rotation-Equivariant Features
• Weakly Supervised Deep Functional Map for Shape Matching