Implicit field supervision for robust non-rigid shape matching

TL;DR

This paper introduces a robust shape matching method using an auto-decoder framework with signed distance regularization, effectively handling real-world challenges like noise and occlusion without data augmentation.

Contribution

It presents a novel shape analysis approach that learns a continuous deformation field with implicit supervision and regularization, improving robustness in non-rigid shape matching.

Findings

Effective on compromised and real-world data

No data augmentation needed for training

Outperforms existing methods in robustness

Abstract

Establishing a correspondence between two non-rigidly deforming shapes is one of the most fundamental problems in visual computing. Existing methods often show weak resilience when presented with challenges innate to real-world data such as noise, outliers, self-occlusion etc. On the other hand, auto-decoders have demonstrated strong expressive power in learning geometrically meaningful latent embeddings. However, their use in \emph{shape analysis} has been limited. In this paper, we introduce an approach based on an auto-decoder framework, that learns a continuous shape-wise deformation field over a fixed template. By supervising the deformation field for points on-surface and regularising for points off-surface through a novel \emph{Signed Distance Regularisation} (SDR), we learn an alignment between the template and shape \emph{volumes}. Trained on clean water-tight meshes, \emph{without} any data-augmentation, we demonstrate compelling performance on compromised data and real-world scans.