Robust Structure-based Shape Correspondence

TL;DR

This paper introduces a robust, efficient method for establishing shape correspondences at the region level, invariant to geometric variations and applicable across different shape representations, by leveraging simplified shape graphs and adapted graph-matching techniques.

Contribution

The novel approach jointly decomposes shapes into simplified graphs and employs an adapted graph-matching technique to find invariant, cross-representation shape correspondences, improving robustness and efficiency.

Findings

Achieves comparable or superior performance on benchmarks.

Handles different shape representations like meshes and point clouds.

Faster and more robust than existing methods.

Abstract

We present a robust method to find region-level correspondences between shapes, which are invariant to changes in geometry and applicable across multiple shape representations. We generate simplified shape graphs by jointly decomposing the shapes, and devise an adapted graph-matching technique, from which we infer correspondences between shape regions. The simplified shape graphs are designed to primarily capture the overall structure of the shapes, without reflecting precise information about the geometry of each region, which enables us to find correspondences between shapes that might have significant geometric differences. Moreover, due to the special care we take to ensure the robustness of each part of our pipeline, our method can find correspondences between shapes with different representations, such as triangular meshes and point clouds. We demonstrate that the region-wise matching that we obtain can be used to find correspondences between feature points, reveal the intrinsic self-similarities of each shape, and even construct point-to-point maps across shapes. Our method is both time and space efficient, leading to a pipeline that is significantly faster than comparable approaches. We demonstrate the performance of our approach through an extensive quantitative and qualitative evaluation on several benchmarks where we achieve comparable or superior performance to existing methods.