Salvato in:
Dettagli Bibliografici
Autori principali: Li, Baoxing, Deng, Yong, Yang, Yehui, Zhao, Xu
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2401.16810
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914868510064640
author Li, Baoxing
Deng, Yong
Yang, Yehui
Zhao, Xu
author_facet Li, Baoxing
Deng, Yong
Yang, Yehui
Zhao, Xu
contents To reconstruct a 3D human surface from a single image, it is crucial to simultaneously consider human pose, shape, and clothing details. Recent approaches have combined parametric body models (such as SMPL), which capture body pose and shape priors, with neural implicit functions that flexibly learn clothing details. However, this combined representation introduces additional computation, e.g. signed distance calculation in 3D body feature extraction, leading to redundancy in the implicit query-and-infer process and failing to preserve the underlying body shape prior. To address these issues, we propose a novel IUVD-Feedback representation, consisting of an IUVD occupancy function and a feedback query algorithm. This representation replaces the time-consuming signed distance calculation with a simple linear transformation in the IUVD space, leveraging the SMPL UV maps. Additionally, it reduces redundant query points through a feedback mechanism, leading to more reasonable 3D body features and more effective query points, thereby preserving the parametric body prior. Moreover, the IUVD-Feedback representation can be embedded into any existing implicit human reconstruction pipeline without requiring modifications to the trained neural networks. Experiments on the THuman2.0 dataset demonstrate that the proposed IUVD-Feedback representation improves the robustness of results and achieves three times faster acceleration in the query-and-infer process. Furthermore, this representation holds potential for generative applications by leveraging its inherent semantic information from the parametric body model.
format Preprint
id arxiv_https___arxiv_org_abs_2401_16810
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Embeddable Implicit IUVD Representation for Part-based 3D Human Surface Reconstruction
Li, Baoxing
Deng, Yong
Yang, Yehui
Zhao, Xu
Computer Vision and Pattern Recognition
To reconstruct a 3D human surface from a single image, it is crucial to simultaneously consider human pose, shape, and clothing details. Recent approaches have combined parametric body models (such as SMPL), which capture body pose and shape priors, with neural implicit functions that flexibly learn clothing details. However, this combined representation introduces additional computation, e.g. signed distance calculation in 3D body feature extraction, leading to redundancy in the implicit query-and-infer process and failing to preserve the underlying body shape prior. To address these issues, we propose a novel IUVD-Feedback representation, consisting of an IUVD occupancy function and a feedback query algorithm. This representation replaces the time-consuming signed distance calculation with a simple linear transformation in the IUVD space, leveraging the SMPL UV maps. Additionally, it reduces redundant query points through a feedback mechanism, leading to more reasonable 3D body features and more effective query points, thereby preserving the parametric body prior. Moreover, the IUVD-Feedback representation can be embedded into any existing implicit human reconstruction pipeline without requiring modifications to the trained neural networks. Experiments on the THuman2.0 dataset demonstrate that the proposed IUVD-Feedback representation improves the robustness of results and achieves three times faster acceleration in the query-and-infer process. Furthermore, this representation holds potential for generative applications by leveraging its inherent semantic information from the parametric body model.
title An Embeddable Implicit IUVD Representation for Part-based 3D Human Surface Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.16810