A Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshes
This work addresses the challenge of efficient and high-fidelity geometry processing for 3D computer vision and graphics, though it appears incremental as it builds on existing methods without a major paradigm shift.
The authors tackled the problem of representing 3D geometry for machine learning on unstructured meshes by proposing a simple, direct encoding approach that avoids resampling, and they achieved highly competitive results in intrinsic shape correspondence estimation.
The question of representation of 3D geometry is of vital importance when it comes to leveraging the recent advances in the field of machine learning for geometry processing tasks. For common unstructured surface meshes state-of-the-art methods rely on patch-based or mapping-based techniques that introduce resampling operations in order to encode neighborhood information in a structured and regular manner. We investigate whether such resampling can be avoided, and propose a simple and direct encoding approach. It does not only increase processing efficiency due to its simplicity - its direct nature also avoids any loss in data fidelity. To evaluate the proposed method, we perform a number of experiments in the challenging domain of intrinsic, non-rigid shape correspondence estimation. In comparisons to current methods we observe that our approach is able to achieve highly competitive results.