ReWeaver：面向仿真就绪与拓扑准确的服装重建
ReWeaver: Towards Simulation-Ready and Topology-Accurate Garment Reconstruction
把服装从无结构表示（3DGS）转为带缝合结构与纸样拓扑的 2D-3D 结构化表示，可直接用于物理仿真与机器人操作；其 UV 空间面板/缝线预测与多视图对齐思路可迁移到其他需仿真就绪的柔性物体重建任务。
原文依据 ReWeaver predicts seams and panels as well as their connectivities in both the 2D UV space and the 3D space.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论高质量的三维服装重建在缩小数字人、虚拟试衣与机器人操作等应用中的仿真到现实差距方面起着关键作用。然而，现有的服装重建方法通常依赖无结构表示，例如三维高斯泼溅，难以对服装拓扑与缝合结构给出准确重建。因此，重建结果往往不适合高保真物理仿真。我们提出 ReWeaver，一个从稀疏多视图 RGB 图像进行拓扑准确的三维服装与缝纫纸样重建的新框架。在仅给定四个输入视图的情况下，ReWeaver 在二维 UV 空间与三维空间中同时预测缝线与面板及其连接关系。预测的缝线与面板与多视图图像精确对齐，产生适用于三维感知、高保真物理仿真与机器人操作的结构化二维-三维服装表示。为支持有效训练，我们构建了大规模数据集 GCD-TS，包含多视图 RGB 图像、三维服装几何、带纹理的人体网格以及标注的缝纫纸样。该数据集包含超过 100,000 个合成样本，覆盖广泛的复杂几何与拓扑。大量实验表明，ReWeaver 在拓扑准确度、几何对齐与缝线-面板一致性方面持续优于现有方法。代码与数据将在项目主页 sii-liming.github.io/ReWeaver 发布。
英文原文摘要 1525 字符
High-quality 3D garment reconstruction plays a crucial role in mitigating the sim-to-real gap in applications such as digital avatars, virtual try-on and robotic manipulation. However, existing garment reconstruction methods typically rely on unstructured representations, such as 3D Gaussian Splats, struggling to provide accurate reconstructions of garment topology and sewing structures. As a result, the reconstructed outputs are often unsuitable for high-fidelity physical simulation. We propose ReWeaver, a novel framework for topology-accurate 3D garment and sewing pattern reconstruction from sparse multi-view RGB images. Given as few as four input views, ReWeaver predicts seams and panels as well as their connectivities in both the 2D UV space and the 3D space. The predicted seams and panels align precisely with the multi-view images, yielding structured 2D-3D garment representations suitable for 3D perception, high-fidelity physical simulation, and robotic manipulation.To enable effective training, we construct a large-scale dataset GCD-TS, comprising multi-view RGB images, 3D garment geometries, textured human body meshes and annotated sewing patterns. The dataset contains over 100,000 synthetic samples covering a wide range of complex geometries and topologies. Extensive experiments show that ReWeaver consistently outperforms existing methods in terms of topology accuracy, geometry alignment and seam-panel consistency. Code and data will be available at the project sii-liming.github.io/ReWeaver.