SMPL Normal Map Is All You Need for Single-view Textured Human Reconstruction

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Shen, Wenhao, Zhang, Gangjian, Zhang, Jianfeng, Feng, Yu, Yao, Nanjie, Zhang, Xuanmeng, Wang, Hao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912431724298240
author Shen, Wenhao
Zhang, Gangjian
Zhang, Jianfeng
Feng, Yu
Yao, Nanjie
Zhang, Xuanmeng
Wang, Hao
author_facet Shen, Wenhao
Zhang, Gangjian
Zhang, Jianfeng
Feng, Yu
Yao, Nanjie
Zhang, Xuanmeng
Wang, Hao
contents Single-view textured human reconstruction aims to reconstruct a clothed 3D digital human by inputting a monocular 2D image. Existing approaches include feed-forward methods, limited by scarce 3D human data, and diffusion-based methods, prone to erroneous 2D hallucinations. To address these issues, we propose a novel SMPL normal map Equipped 3D Human Reconstruction (SEHR) framework, integrating a pretrained large 3D reconstruction model with human geometry prior. SEHR performs single-view human reconstruction without using a preset diffusion model in one forward propagation. Concretely, SEHR consists of two key components: SMPL Normal Map Guidance (SNMG) and SMPL Normal Map Constraint (SNMC). SNMG incorporates SMPL normal maps into an auxiliary network to provide improved body shape guidance. SNMC enhances invisible body parts by constraining the model to predict an extra SMPL normal Gaussians. Extensive experiments on two benchmark datasets demonstrate that SEHR outperforms existing state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12793
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SMPL Normal Map Is All You Need for Single-view Textured Human Reconstruction
Shen, Wenhao
Zhang, Gangjian
Zhang, Jianfeng
Feng, Yu
Yao, Nanjie
Zhang, Xuanmeng
Wang, Hao
Computer Vision and Pattern Recognition
Single-view textured human reconstruction aims to reconstruct a clothed 3D digital human by inputting a monocular 2D image. Existing approaches include feed-forward methods, limited by scarce 3D human data, and diffusion-based methods, prone to erroneous 2D hallucinations. To address these issues, we propose a novel SMPL normal map Equipped 3D Human Reconstruction (SEHR) framework, integrating a pretrained large 3D reconstruction model with human geometry prior. SEHR performs single-view human reconstruction without using a preset diffusion model in one forward propagation. Concretely, SEHR consists of two key components: SMPL Normal Map Guidance (SNMG) and SMPL Normal Map Constraint (SNMC). SNMG incorporates SMPL normal maps into an auxiliary network to provide improved body shape guidance. SNMC enhances invisible body parts by constraining the model to predict an extra SMPL normal Gaussians. Extensive experiments on two benchmark datasets demonstrate that SEHR outperforms existing state-of-the-art methods.
title SMPL Normal Map Is All You Need for Single-view Textured Human Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.12793