通过等变紧致性建模，实现衣物人体拟合的高精度与强泛化。
ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness
- 利用局部SE(3)等变性建立衣物到身体的映射关系。
- 在松散衣物上精度提升16.7%~69.5%，平均形状误差降低49.9%。
- 适用于复杂姿态、新形状和非刚性动态，适合动作捕捉与虚拟试衣。
将人体拟合到3D衣物点云是常见但具有挑战性的任务。传统基于优化的方法依赖多阶段流程，对姿态初始化敏感；而近年学习方法在不同姿态与服装类型间泛化能力不足。本文提出等变紧致性拟合方法（ETCH），通过局部近似SE(3)等变性，将紧致性编码为从衣物表面到底层身体的位移向量，进而估计衣物-身体表面映射。在此基础上，回归姿态无关的身体特征点，将拟合简化为内层身体特征点拟合任务。在CAPE与4D-Dress数据集上的实验表明，ETCH显著优于现有最先进方法——在松散衣物上体表拟合精度提升16.7%~69.5%，平均形状精度提升49.9%。其等变紧致性设计甚至在单次输入（或分布外）设置下将方向误差减少67.2%~89.8%（仅用约1%数据）。定性结果表明，无论面对复杂姿态、未见形状、松散衣物或非刚性运动，该方法均表现出强大泛化能力。代码与模型将很快发布于https://boqian-li.github.io/ETCH/。
原文摘要 · Abstract (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 (~ 1% data). 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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。