高斯中的抓取：从单目视频快速重建动态手-物体交互
Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions
AI总结：
本文提出GraG方法，通过高效跟踪手和物体实现快速动态3D重建，采用紧凑的高斯求和表示提升效率并保持几何精度，实验表明其在长序列中速度提升6.4倍，物体重建精度提高13.4%。
摘要：
我们提出了Grasp in Gaussians (GraG)，一种从单目视频快速且稳健地重建动态3D手-物体交互的方法。与近期优化重型神经表示的方法不同，我们的方法在初始化自预训练大模型后，高效跟踪手和物体。关键洞察是使用紧凑的高斯求和（SoG）表示恢复准确且时间稳定的hand-object运动，该表示源自经典跟踪文献并整合了生成高斯基于的初始化。我们使用视频适应的SAM3D流程初始化物体姿态和几何，然后将结果密集的高斯表示转换为轻量级SoG通过下采样。这种紧凑的表示使高效快速跟踪并保持几何保真度。对于手部，我们采用互补策略：从现成的单目手部姿态初始化开始，使用简单但有效的2D关节和深度对齐损失来细化手部运动，避免对详细3D手部外观模型进行每帧细化，同时保持稳定的关节运动。在公共基准上的大量实验表明，GraG在长序列中比先前工作快6.4倍重建时间，同时提高物体重建精度13.4%，并将手部每个关节位置误差减少超过65%。
英文摘要：
We present Grasp in Gaussians (GraG), a fast and robust method for reconstructing dynamic 3D hand-object interactions from a single monocular video. Unlike recent approaches that optimize heavy neural representations, our method focuses on tracking the hand and the object efficiently, once initialized from pretrained large models. Our key insight is that, given strong pretrained object and hand priors, accurate and temporally stable hand-object motion can be recovered using a compact Sum-of-Gaussians (SoG) representation, revived from classical tracking literature and integrated with generative Gaussian-based initializations. We initialize object pose and geometry using a video-adapted SAM3D pipeline, then convert the resulting dense Gaussian representation into a lightweight SoG via subsampling. This compact representation enables efficient and fast tracking while preserving geometric fidelity, with the pretrained priors and simple geometric/contact losses providing accurate hand-object placement. For the hand, we adopt a complementary strategy: starting from off-the-shelf monocular hand pose initialization, we refine hand motion using simple yet effective 2D joint, silhouette, depth, and contact losses, avoiding per-frame refinement of a detailed 3D hand appearance model while maintaining stable articulation. Extensive experiments on public benchmarks demonstrate that GraG reconstructs temporally coherent hand-object interactions on long sequences 4.4x-38.9x faster than prior work while preserving temporally coherent hand-object motion.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
