Shape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching via Unsupervised Functional Map Regularized Reconstruction

TL;DR

SNK introduces a zero-shot, unsupervised method for non-rigid shape matching that reconstructs shapes via an encoder-decoder architecture and functional map regularization, eliminating the need for training data.

Contribution

It proposes a novel zero-shot approach using unsupervised functional map regularization within an encoder-decoder framework for shape matching.

Findings

Achieves competitive results on standard benchmarks.

Simplifies non-rigid shape matching without training data.

Uses a new decoder architecture for smooth deformations.

Abstract

We present Shape Non-rigid Kinematics (SNK), a novel zero-shot method for non-rigid shape matching that eliminates the need for extensive training or ground truth data. SNK operates on a single pair of shapes, and employs a reconstruction-based strategy using an encoder-decoder architecture, which deforms the source shape to closely match the target shape. During the process, an unsupervised functional map is predicted and converted into a point-to-point map, serving as a supervisory mechanism for the reconstruction. To aid in training, we have designed a new decoder architecture that generates smooth, realistic deformations. SNK demonstrates competitive results on traditional benchmarks, simplifying the shape-matching process without compromising accuracy. Our code can be found online: https://github.com/pvnieo/SNK