文献类型：期刊文献

英文题名：Uncertainty-Aware Adjustment via Learnable Coefficients for Detailed 3D Reconstruction of Clothed Humans from Single Images

作者：Yang, Yadan[1];Li, Yunze[1];Ying, Fangli[1];Phaphuangwittayakul, Aniwat[2];Dhuny, Riyad[3]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai, Peoples R China;[2]Chiang Mai Univ, Int Coll Digital Innovat, Chiang Mai, Thailand;[3]Univ Technol Mauritius, Reduit, Mauritius

年份：2025

卷号：44

期号：7

外文期刊名：COMPUTER GRAPHICS FORUM

收录：;EI(收录号：20254219324944);WOS:【SCI-EXPANDED(收录号:WOS:001590874600001)】；

基金：This research was funded by the National Major Scientific Instruments and Equipment Development Project of the National Natural Science Foundation of China (No. 32327801). It was also partially supported by the National Key Research and Development Program of China (No. 2020YFA0907800), the Research and Development Plan in Shandong Province (No. 2022CXGC020206), and the Key R&D Program of Shandong Province, China (No. 2022SFGC0104).r No Statement Availabler No Statement Availabler No Statement Availabler No Statement Available

语种：英文

外文关键词：CCS Concepts; center dot Computing methodologies -> Mesh models

摘要：Although single-image 3D human reconstruction has made significant progress in recent years, few of the current state-of-the-art methods can accurately restore the appearance and geometric details of loose clothing. To achieve high-quality reconstruction of a human body wearing loose clothing, we propose a learnable dynamic adjustment framework that integrates side-view features and the uncertainty of the parametric human body model to adaptively regulate its reliability based on the clothing type. Specifically, we first adopt the Vision Transformer model as an encoder to capture the image features of the input image, and then employ SMPL-X to decouple the side-view body features. Secondly, to reduce the limitations imposed by the regularization of the parametric model, particularly for loose garments, we introduce a learnable coefficient to reduce the reliance on SMPL-X. This strategy effectively accommodates the large deformations caused by loose clothing, thereby accurately expressing the posture and clothing in the image. To evaluate the effectiveness, we validate our method on the public CLOTH4D and Cape datasets, and the experimental results demonstrate better performance compared to existing approaches. The code is available at https://github.com/yyd0613/CoRe-Human.