Unsupervised Dense Deformation Embedding Network for Template-Free Shape Correspondence

08/26/2021
by   Ronghan Chen, et al.
0

Shape correspondence from 3D deformation learning has attracted appealing academy interests recently. Nevertheless, current deep learning based methods require the supervision of dense annotations to learn per-point translations, which severely overparameterize the deformation process. Moreover, they fail to capture local geometric details of original shape via global feature embedding. To address these challenges, we develop a new Unsupervised Dense Deformation Embedding Network (i.e., UD^2E-Net), which learns to predict deformations between non-rigid shapes from dense local features. Since it is non-trivial to match deformation-variant local features for deformation prediction, we develop an Extrinsic-Intrinsic Autoencoder to frst encode extrinsic geometric features from source into intrinsic coordinates in a shared canonical shape, with which the decoder then synthesizes corresponding target features. Moreover, a bounded maximum mean discrepancy loss is developed to mitigate the distribution divergence between the synthesized and original features. To learn natural deformation without dense supervision, we introduce a coarse parameterized deformation graph, for which a novel trace and propagation algorithm is proposed to improve both the quality and effciency of the deformation. Our UD^2E-Net outperforms state-of-the-art unsupervised methods by 24 Inter challenge and even supervised methods by 13

READ FULL TEXT

page 14

page 15

research
07/19/2022

MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views

We propose MHR-Net, a novel method for recovering Non-Rigid Shapes from ...
research
06/26/2020

Meta Deformation Network: Meta Functionals for Shape Correspondence

We present a new technique named "Meta Deformation Network" for 3D shape...
research
05/23/2020

MeshODE: A Robust and Scalable Framework for Mesh Deformation

We present MeshODE, a scalable and robust framework for pairwise CAD mod...
research
12/29/2022

Learning Implicit Functions for Dense 3D Shape Correspondence of Generic Objects

The objective of this paper is to learn dense 3D shape correspondence fo...
research
08/23/2023

Semantic-Aware Implicit Template Learning via Part Deformation Consistency

Learning implicit templates as neural fields has recently shown impressi...
research
09/13/2023

Digital 3D Smocking Design

We develop an optimization-based method to model smocking, a surface emb...
research
10/23/2020

Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence

The goal of this paper is to learn dense 3D shape correspondence for top...

Please sign up or login with your details

Forgot password? Click here to reset