USTNet: Unsupervised Shape-to-Shape Translation via Disentangled Representations

Haoran Wang, Jiaxin Li, Alexandru Telea, Jiri Kosinka, Zizhao Wu*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

1 Citation (Scopus)
272 Downloads (Pure)

Abstract

We propose USTNet, a novel deep learning approach designed for learning shape-to-shape translation from unpaired domains in an unsupervised manner. The core of our approach lies in disentangled representation learning that factors out the discriminative features of 3D shapes into content and style codes. Given input shapes from multiple domains, USTNet disentangles their representation into style codes that contain distinctive traits across domains and content codes that contain domaininvariant traits. By fusing the style and content codes of the target and source shapes, our method enables us to synthesize new shapes that resemble the target style and retain the content features of source shapes. Based on the shared style space, our method facilitates shape interpolation by manipulating the style attributes from different domains. Furthermore, by extending the basic building blocks of our network from two-class to multi-class classification, we adapt USTNet to tackle multi-domain shape-to-shape translation. Experimental results show that our approach can generate realistic and natural translated shapes and that our method leads to improved quantitative evaluation metric results compared to 3DSNet. Codes are available at https://Haoran226.github.io/USTNet.
Original languageEnglish
Pages (from-to)141-152
Number of pages12
JournalComputer Graphics Forum
Volume41
Issue number7
DOIs
Publication statusPublished - 2022

Fingerprint

Dive into the research topics of 'USTNet: Unsupervised Shape-to-Shape Translation via Disentangled Representations'. Together they form a unique fingerprint.

Cite this