仅用单张图像重建多层衣物3D人体，无需特殊设备。
ReMu: Reconstructing Multi-layer 3D Clothed Human from Image Layers
- 通过图像层输入，统一建模各层衣物的3D结构。
- 实现近零穿插的多层衣物重建，效果媲美专用方法。
- 无需模板或类别限制，适配各类服装风格。
多层3D衣物重建通常依赖昂贵的多视角采集设备和专门的3D编辑工作。为构建逼真穿衣人体虚拟形象，我们提出ReMu，在新型图像层（Image Layers）设置下，仅用单个RGB相机捕捉穿戴多层衣物的主体。为实现物理合理的多层3D衣物建模，需统一的3D表示以分层建模。我们首先在标准体态坐标系中重建并对齐每层衣物；随后引入碰撞感知优化流程，利用隐式神经场解决衣物穿插问题，并精炼边界。该方法无需模板且类别无关，可重建多样服装风格。实验表明，其能生成近乎无穿插的3D穿衣人体，性能媲美专用方法。
原文摘要 · Abstract (English)
The reconstruction of multi-layer 3D garments typically requires expensive multi-view capture setups and specialized 3D editing efforts. To support the creation of life-like clothed human avatars, we introduce ReMu for reconstructing multi-layer clothed humans in a new setup, Image Layers, which captures a subject wearing different layers of clothing with a single RGB camera. To reconstruct physically plausible multi-layer 3D garments, a unified 3D representation is necessary to model these garments in a layered manner. Thus, we first reconstruct and align each garment layer in a shared coordinate system defined by the canonical body pose. Afterwards, we introduce a collision-aware optimization process to address interpenetration and further refine the garment boundaries leveraging implicit neural fields. It is worth noting that our method is template-free and category-agnostic, which enables the reconstruction of 3D garments in diverse clothing styles. Through our experiments, we show that our method reconstructs nearly penetration-free 3D clothed humans and achieves competitive performance compared to category-specific methods. Project page: https://eth-ait.github.io/ReMu/
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。