面向单张图像的人类交互感知三维重建
Human Interaction-Aware 3D Reconstruction from a Single Image
把多人场景先变换到正交规范空间、再用多视图扩散联合生成法线与图像以补全遮挡区域，并引入基于物理的交互先验约束人体间接触，这套「组-实例联合建模 + 多视图扩散补全」思路可直接迁移到多人/多物体场景的单图重建与遮挡补全任务。
原文依据 generates complete multi-view normals and images by jointly modeling individuals and group context to resolve occlusions and proximity
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从单张图像重建带纹理的三维人体模型是 AR/VR 与数字人应用的基础。然而，现有方法大多只关注单个人体，因而在多人场景中失效：简单地将单个人体重建结果组合起来，往往会产生不真实的相互穿插、遮挡区域几何缺失以及交互关系扭曲等伪影。这些局限凸显了引入群体级上下文与交互先验的必要性。我们提出一种整体性方法，显式建模群体级与实例级信息。为缓解透视带来的几何畸变，我们首先将输入变换到规范的正交空间。我们的核心组件「人体群体-实例多视图扩散」（HUG-MVD）随后通过联合建模个体与群体上下文，生成完整的多视图法线与图像，以解决遮挡与邻近问题。接着，「人体群体-实例几何重建」（HUG-GR）模块利用显式的、基于物理的交互先验优化几何，以强制物理合理性并准确建模人与人之间的接触。最后，多视图图像被融合为高保真纹理。这些组件共同构成我们的完整框架 HUG3D。大量实验表明，HUG3D 显著优于单人体方法以及现有多人体方法，能够从单张图像生成物理合理、高保真的相互交互人物的三维重建结果。
英文原文摘要 1531 字符
Reconstructing textured 3D human models from a single image is fundamental for AR/VR and digital human applications. However, existing methods mostly focus on single individuals and thus fail in multi-human scenes, where naive composition of individual reconstructions often leads to artifacts such as unrealistic overlaps, missing geometry in occluded regions, and distorted interactions. These limitations highlight the need for approaches that incorporate group-level context and interaction priors. We introduce a holistic method that explicitly models both group- and instance-level information. To mitigate perspective-induced geometric distortions, we first transform the input into a canonical orthographic space. Our primary component, Human Group-Instance Multi-View Diffusion (HUG-MVD), then generates complete multi-view normals and images by jointly modeling individuals and group context to resolve occlusions and proximity. Subsequently, the Human Group-Instance Geometric Reconstruction (HUG-GR) module optimizes the geometry by leveraging explicit, physics-based interaction priors to enforce physical plausibility and accurately model inter-human contact. Finally, the multi-view images are fused into a high-fidelity texture. Together, these components form our complete framework, HUG3D. Extensive experiments show that HUG3D significantly outperforms both single-human and existing multi-human methods, producing physically plausible, high-fidelity 3D reconstructions of interacting people from a single image.