ReMu: Reconstructing Multi-layer 3D Clothed Human from Image Layers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vuran, Onat, Ho, Hsuan-I
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909718931308544
author Vuran, Onat
Ho, Hsuan-I
author_facet Vuran, Onat
Ho, Hsuan-I
contents The reconstruction of multi-layer 3D garments typically requires expensive multi-view capture setups and specialized 3D editing efforts. To support the creation of life-like clothed human avatars, we introduce ReMu for reconstructing multi-layer clothed humans in a new setup, Image Layers, which captures a subject wearing different layers of clothing with a single RGB camera. To reconstruct physically plausible multi-layer 3D garments, a unified 3D representation is necessary to model these garments in a layered manner. Thus, we first reconstruct and align each garment layer in a shared coordinate system defined by the canonical body pose. Afterwards, we introduce a collision-aware optimization process to address interpenetration and further refine the garment boundaries leveraging implicit neural fields. It is worth noting that our method is template-free and category-agnostic, which enables the reconstruction of 3D garments in diverse clothing styles. Through our experiments, we show that our method reconstructs nearly penetration-free 3D clothed humans and achieves competitive performance compared to category-specific methods. Project page: https://eth-ait.github.io/ReMu/
format Preprint
id arxiv_https___arxiv_org_abs_2508_01381
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReMu: Reconstructing Multi-layer 3D Clothed Human from Image Layers
Vuran, Onat
Ho, Hsuan-I
Graphics
Computer Vision and Pattern Recognition
The reconstruction of multi-layer 3D garments typically requires expensive multi-view capture setups and specialized 3D editing efforts. To support the creation of life-like clothed human avatars, we introduce ReMu for reconstructing multi-layer clothed humans in a new setup, Image Layers, which captures a subject wearing different layers of clothing with a single RGB camera. To reconstruct physically plausible multi-layer 3D garments, a unified 3D representation is necessary to model these garments in a layered manner. Thus, we first reconstruct and align each garment layer in a shared coordinate system defined by the canonical body pose. Afterwards, we introduce a collision-aware optimization process to address interpenetration and further refine the garment boundaries leveraging implicit neural fields. It is worth noting that our method is template-free and category-agnostic, which enables the reconstruction of 3D garments in diverse clothing styles. Through our experiments, we show that our method reconstructs nearly penetration-free 3D clothed humans and achieves competitive performance compared to category-specific methods. Project page: https://eth-ait.github.io/ReMu/
title ReMu: Reconstructing Multi-layer 3D Clothed Human from Image Layers
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.01381