Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

STAR-TM: STructure aware reconstruction of textured mesh from single image

Wu, Tong, Gao, Lin, Zhang, Ling-Xiao, Lai, YuKun ORCID: https://orcid.org/0000-0002-2094-5680 and Zhang, Hao 2023. STAR-TM: STructure aware reconstruction of textured mesh from single image. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 (12) , pp. 15680-15693. 10.1109/TPAMI.2023.3305630

[thumbnail of STAR-TM_TPAMI.pdf]
Preview
PDF - Accepted Post-Print Version
Download (9MB) | Preview

Abstract

We present a novel method for single-view 3D reconstruction of textured meshes , with a focus to address the primary challenge surrounding texture inference and transfer. Our key observation is that learning textured reconstruction in a structure-aware and globally consistent manner is effective in handling the severe ill-posedness of the texturing problem and significant variations in object pose and texture details. Specifically, we perform structured mesh reconstruction, via a retrieval-and-assembly approach, to produce a set of genus-zero parts parameterized by deformable boxes and endowed with semantic information. For texturing, we first transfer visible colors from the input image onto the unified UV texture space of the deformable boxes. Then we combine a learned transformer model for per-part texture completion with a global consistency loss to optimize inter-part texture consistency. Our texture completion model operates in a VQ-VAE embedding space and is trained end-to-end, with the transformer training enhanced with retrieved texture instances to improve texture completion performance amid significant occlusion. Extensive experiments demonstrate higher-quality textured mesh reconstruction obtained by our method over state-of-the-art alternatives, both quantitatively and qualitatively, as reflected by a better recovery of texture coherence and details.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Publisher: Institute of Electrical and Electronics Engineers
ISSN: 0162-8828
Funders: The Royal Society
Date of First Compliant Deposit: 20 September 2023
Date of Acceptance: 29 July 2023
Last Modified: 14 Dec 2023 03:32
URI: https://orca.cardiff.ac.uk/id/eprint/162652

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics