TM-NET: Deep generative networks for textured meshes

Geo, Lin, Wu, Tong, Yuan, Yu-Jie, Lin, Ming-Xian, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 and Zhang, Hao 2021. TM-NET: Deep generative networks for textured meshes. ACM Transactions on Graphics 40 (6) , 263. 10.1145/3478513.3480503

PDF - Accepted Post-Print Version Download (12MB)

Abstract

We introduce TM-NET, a novel deep generative model for synthesizing textured meshes in a part-aware manner. Once trained, the network can generate novel textured meshes from scratch or predict textures for a given 3D mesh, without image guidance. Plausible and diverse textures can be generated for the same mesh part, while texture compatibility between parts in the same shape is achieved via conditional generation. Specifically, our method produces texture maps for individual shape parts, each as a deformable box, leading to a natural UV map with limited distortion. The network separately embeds part geometry (via a PartVAE) and part texture (via a TextureVAE) into their respective latent spaces, so as to facilitate learning texture probability distributions conditioned on geometry. We introduce a conditional autoregressive model for texture generation, which can be conditioned on both part geometry and textures already generated for other parts to achieve texture compatibility. To produce high-frequency texture details, our TextureVAE operates in a high-dimensional latent space via dictionary-based vector quantization. We also exploit transparencies in the texture as an effective means to model complex shape structures including topological details. Extensive experiments demonstrate the plausibility, quality, and diversity of the textures and geometries generated by our network, while avoiding inconsistency issues that are common to novel view synthesis methods.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Association for Computing Machinery (ACM)
ISSN:	0730-0301
Funders:	Royal Society
Date of First Compliant Deposit:	13 September 2021
Date of Acceptance:	5 September 2021
Last Modified:	03 Dec 2024 00:45
URI:	https://orca.cardiff.ac.uk/id/eprint/144070

Citation Data

Cited 12 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item