arXiv cs.AI· Nanxiang Jiang, Yunuo Chen, Zeng Tao, Zizhang Li, Qi Guo, Jiajun Wu, Yin Yang, Chenfanfu Jiang·· 3 天前AI 评分20
DressAgent：用视觉智能体实现逆向服装设计
Inverse Garment Design with Visual Agents
AI 导读
研究团队提出 DressAgent，一个基于视觉智能体的分层系统，可从单张图像重建可仿真的任意层数 3D 服装缝纫纸样。该方法基于 GarmentCode 构建了首个超 15K 套服装的多层缝纫纸样数据集，通过图层规划与 Tailor、Critic、Orchestrator 智能体闭环细化，大幅超越前馈方法，并在远少于可微优化的时间内达到或超过其效果。
正文 · 原文
Abstract:We study the problem of inverse garment design, reconstructing simulation-ready 3D outfits with arbitrary layers from a single image, with visual agents. Unlike differentiable optimization that is time-consuming, or feed-forward methods limited by training data, we introduce DressAgent, a hierarchical agentic system that recovers garment sewing patterns through planning and closed-loop refinement grounded in physical simulation. To this end, we first present an enhanced representation based on GarmentCode for diverse styles and arbitrary dressing layers, and build the first multi-layer sewing pattern dataset with over 15K outfits for supervision and benchmarking. Inverse design then proceeds coarse to fine: In layer planning and coarse estimation, agents infer layer order and relations, peel each layer into its own view, and estimate coarse patterns. In fine-grained refinement, an agentic trio of Tailor, Critic, and Orchestrator refines patterns in a closed loop of editing, simulating, and judging against the reference with visual and measured evidence. Carefully designed tools and an evolving memory make this refinement converge on the target geometry. We also design an agentic generation method for high-fidelity textures. DressAgent outperforms feed-forward methods by a large margin, surpasses or matches differentiable optimization in a fraction of the time, and generalizes to complex layering, diverse poses, and body shapes.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.15582 [cs.AI] |
| (or arXiv:2610.15582v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.15582 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiang Nanxiang [view email]
[v1]
Sun, 11 Oct 2026 12:55:06 UTC (17,769 KB)
来源：arXiv cs.AI · arxiv.org