ETCH：通過等變緊緻性將身體擬合推廣至著衣人體

ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness

March 13, 2025

作者: Boqian Li, Haiwen Feng, Zeyu Cai, Michael J. Black, Yuliang Xiu

cs.AI

摘要

將人體擬合到三維著衣人體點雲是一項常見但具有挑戰性的任務。傳統基於優化的方法採用多階段流程，這些流程對姿態初始化敏感，而最近的學習方法往往難以在各種姿態和服裝類型之間實現泛化。我們提出了等變緊密度擬合著衣人體（Equivariant Tightness Fitting for Clothed Humans，簡稱ETCH），這是一種新穎的流程，通過局部近似SE(3)等變性來估計布料到體表的映射，將緊密度編碼為從布料表面到內在身體的位移向量。根據此映射，姿態不變的身體特徵回歸稀疏的身體標記，將著衣人體擬合簡化為內在身體標記擬合任務。在CAPE和4D-Dress上的大量實驗表明，ETCH在寬鬆服裝的身體擬合精度（16.7% ~ 69.5%）和形狀精度（平均49.9%）上顯著優於最先進的方法——無論是無視緊密度還是考慮緊密度的方法。我們的等變緊密度設計甚至可以在一次性（或分佈外）設置中將方向誤差減少（67.2% ~ 89.8%）。定性結果展示了ETCH在面對挑戰性姿態、未見過的形狀、寬鬆服裝和非剛性動力學時的強大泛化能力。我們將很快在https://boqian-li.github.io/ETCH/上發布代碼和模型以供研究用途。

English

Fitting a body to a 3D clothed human point cloud is a common yet challenging task. Traditional optimization-based approaches use multi-stage pipelines that are sensitive to pose initialization, while recent learning-based methods often struggle with generalization across diverse poses and garment types. We propose Equivariant Tightness Fitting for Clothed Humans, or ETCH, a novel pipeline that estimates cloth-to-body surface mapping through locally approximate SE(3) equivariance, encoding tightness as displacement vectors from the cloth surface to the underlying body. Following this mapping, pose-invariant body features regress sparse body markers, simplifying clothed human fitting into an inner-body marker fitting task. Extensive experiments on CAPE and 4D-Dress show that ETCH significantly outperforms state-of-the-art methods -- both tightness-agnostic and tightness-aware -- in body fitting accuracy on loose clothing (16.7% ~ 69.5%) and shape accuracy (average 49.9%). Our equivariant tightness design can even reduce directional errors by (67.2% ~ 89.8%) in one-shot (or out-of-distribution) settings. Qualitative results demonstrate strong generalization of ETCH, regardless of challenging poses, unseen shapes, loose clothing, and non-rigid dynamics. We will release the code and models soon for research purposes at https://boqian-li.github.io/ETCH/.