T3HG-Editor：基于嵌入SMPL-X人体先验的文本驱动3D人体服装编辑
T3HG-Editor: Text-driven 3D Human Garment Editing with Body Priors Embedded in SMPL-X
浏览论文内容
中文总结 AI 辅助
研究文本驱动的3D人体服装编辑问题，提出T3HG-Editor编辑器，利用SMPL-X的先验信息，经可编辑高斯获取、服装一致编辑、高斯更新带溢出修剪三个阶段，实现高保真和服装一致的编辑效果，优于现有方法。
中文摘要 AI 辅助
尽管3D高斯编辑（3DGE）取得了显著进展，但文本驱动的3D人体服装编辑仍未得到充分探索。现有3DGE工作通常采用将2D编辑技术应用于多视图渲染图像并根据修改后的图像更新3D高斯的范式。将此类方法扩展到3D人体服装编辑会因引入的失真和服装不一致而导致低保真结果。SMPL-X模型为虚拟人体现了丰富的先验信息，带来了一个有前景的突破机会。受此启发，我们提出了一种文本驱动的3D人体服装编辑器T3HG-Editor，它通过利用嵌入SMPL-X的几何和关节先验来提供高保真和服装一致的结果。具体来说，T3HG-Editor包含三个阶段，即可编辑高斯的获取、服装一致编辑以及带溢出修剪的高斯更新。可编辑高斯的获取首先沿着SMPL-X法线播种高斯以生成足够的近表面高斯，然后通过2D掩码约束精确地定位要编辑的目标高斯。服装一致编辑聚合跨多个视图对应于相同SMPL-X顶点的令牌并将它们传播回原始视图，在无需额外训练的情况下强制服装一致性。带溢出修剪的高斯更新使用在SMPL-X上定义的符号距离函数（SDF）来构建人体距离场，然后将其与2D语义掩码集成以修剪溢出的高斯，从而防止非目标区域受到污染。对多个对象和不同服装类型的实验表明，T3HG-Editor在编辑质量和服装一致性方面均优于现有方法。
英文摘要
While 3D Gaussian Editing (3DGE) has seen substantial progress, text-driven 3D human garment editing remains largely underexplored. Existing 3DGE works typically follow a paradigm that applies 2D editing techniques to multi-view rendered images and updates 3D Gaussians based on the modified images. Extending such methods to 3D human garment editing suffers from low-fidelity outcomes, caused by introduced distortions and garment inconsistencies. A promising breakthrough opportunity arises from the SMPL eXpressive (SMPL-X) model that embodies rich prior information for virtual humans. Motivated by this insight, we propose a text-driven 3D human garment editor termed T3HG-Editor, which delivers high-fidelity and garment consistent results by leveraging geometry and joint priors embedded in SMPL-X. Specifically, T3HG-Editor contains three stages, namely obtainment of editable Gaussians, garment consistent editing, and Gaussian updating with overflow pruning. The obtainment of editable Gaussians begins with seeding Gaussians along SMPL-X normals to generate sufficient near surface Gaussians, followed by a 2D mask constraint that precisely localizes the target Gaussians to be edited. The garment consistent editing aggregates tokens corresponding to the same SMPL-X vertex across multiple views and propagates them to their original views, enforcing garment consistency without requiring additional training. Gaussian updating with overflow pruning employs a Signed Distance Function (SDF) defined on SMPL-X to construct a human distance field, which is then integrated with a 2D semantic mask to prune overflowing Gaussians, thus preventing contamination of non-target regions. Experiments on multiple subjects and diverse garment types demonstrate that T3HG-Editor outperforms state-of-the-art methods in both editing quality and garment consistency.
