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

by   Baowen Zhang, et al.

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


page 4

page 8

page 20

page 21

page 22

page 23

page 24

page 25


Deep Implicit Templates for 3D Shape Representation

Deep implicit functions (DIFs), as a kind of 3D shape representation, ar...

Shape correspondences from learnt template-based parametrization

We present a new deep learning approach for matching deformable shapes b...

Semantic-Aware Implicit Template Learning via Part Deformation Consistency

Learning implicit templates as neural fields has recently shown impressi...

A functional skeleton transfer

The animation community has spent significant effort trying to ease rigg...

GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models

This paper introduces GenCorres, a novel unsupervised joint shape matchi...

Implicit field supervision for robust non-rigid shape matching

Establishing a correspondence between two non-rigidly deforming shapes i...

Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapes

We present the first utterly self-supervised network for dense correspon...

Please sign up or login with your details

Forgot password? Click here to reset