Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objects

TL;DR

This paper introduces a self-supervised neural implicit shape representation method for deformable objects that does not require semantic annotations, enabling effective modeling of large deformations and supporting applications like texture transfer and shape editing.

Contribution

The proposed approach learns implicit shape representations without semantic priors, using a novel hierarchical rigid constraint to handle large deformations and local ambiguities.

Findings

Effective representation of shapes with large deformations.

Supports texture transfer and shape editing tasks.

Outperforms existing methods in shape modeling accuracy.

Abstract

Learning 3D shape representation with dense correspondence for deformable objects is a fundamental problem in computer vision. Existing approaches often need additional annotations of specific semantic domain, e.g., skeleton poses for human bodies or animals, which require extra annotation effort and suffer from error accumulation, and they are limited to specific domain. In this paper, we propose a novel self-supervised approach to learn neural implicit shape representation for deformable objects, which can represent shapes with a template shape and dense correspondence in 3D. Our method does not require the priors of skeleton and skinning weight, and only requires a collection of shapes represented in signed distance fields. To handle the large deformation, we constrain the learned template shape in the same latent space with the training shapes, design a new formulation of local rigid constraint that enforces rigid transformation in local region and addresses local reflection issue, and present a new hierarchical rigid constraint to reduce the ambiguity due to the joint learning of template shape and correspondences. Extensive experiments show that our model can represent shapes with large deformations. We also show that our shape representation can support two typical applications, such as texture transfer and shape editing, with competitive performance. The code and models are available at https://iscas3dv.github.io/deformshape