从二维对齐到三维合理性：统一异构二维先验与无穿模扩散实现遮挡鲁棒的双手重建
From 2D Alignment to 3D Plausibility: Unifying Heterogeneous 2D Priors and Penetration-Free Diffusion for Occlusion-Robust Two-Hand Reconstruction
把关键点、分割、深度等视觉基础模型先验以隐式融合编码器吸收，而非作为显式输入，可在不增加基础模型推理成本的前提下提升单目重建精度；同时用带碰撞梯度引导的扩散模型把互穿姿态映射到无碰撞流形，这一「生成式后处理」思路可迁移到人体/多人交互重建与姿态去穿模。
原文依据 a two-hand penetration-free diffusion model that learns a generative mapping from interpenetrated poses to realistic, collision-free configurations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论单目图像中的双手重建受复杂姿态与严重遮挡的制约，常导致交互错位与双手互穿。我们将该问题解耦为二维结构对齐与三维空间交互对齐，并分别由专门设计的组件处理。在二维对齐方面，我们率先尝试统一来自视觉基础模型的异构结构先验（关键点、分割与深度），将其作为双手恢复的互补结构化引导。我们并非把先验预测作为显式输入提取出来，而是提出一种融合对齐编码器，以隐式方式吸收其结构知识，从而在不付出基础模型级代价的情况下获得基础模型级引导。在三维空间对齐方面，我们提出一种无穿模的双手扩散模型，学习从互穿姿态到真实、无碰撞构型的生成式映射。该模型在去噪过程中由碰撞梯度引导，收敛到有效双手交互的流形上，从而保持几何与运动学上的一致性。这种生成式建模方式使得在遮挡或视觉输入存在歧义时仍能获得物理上可信的重建结果。在 InterHand2.6M 与 HIC 上的大量实验表明，该方法在交互对齐与穿模抑制方面达到最优或领先性能。项目主页：https://gaogehan.github.io/A2P/
英文原文摘要 1407 字符
Two-hand reconstruction from monocular images is hampered by complex poses and severe occlusions, which often cause interaction misalignment and two-hand penetration. We address this by decoupling the problem into 2D structural alignment and 3D spatial interaction alignment, each handled by a tailored component. For 2D alignment, we pioneer the attempt to unify heterogeneous structural priors (keypoints, segmentation, and depth) from vision foundation models as complementary structured guidance for two-hand recovery. Instead of extracting priors prediction as explicit inputs, we propose a fusion-alignment encoder that absorbs their structural knowledge implicitly, achieving foundation-level guidance without foundation-level cost. For 3D spatial alignment, we propose a two-hand penetration-free diffusion model that learns a generative mapping from interpenetrated poses to realistic, collision-free configurations. Guided by collision gradients during denoising, the model converges toward the manifold of valid two-hand interactions, preserving geometric and kinematic coherence. This generative formulation approach enables physically credible reconstructions even under occlusion or ambiguous visual input. Extensive experiments on InterHand2.6M and HIC show state-of-the-art or leading performance in interaction alignment and penetration suppression. Project: https://gaogehan.github.io/A2P/