WristCompass: 运动耦合作为可学习的视觉概念用于自我相机朝向估计
WristCompass: Kinematic Coupling as a Learnable Visual Concept for Ego-Camera Orientation
AI总结：
提出WristCompass，利用手腕与相机朝向之间的运动耦合作为视觉概念，通过紧凑的4D特征和GRU时序建模，从操作视频中恢复自我相机朝向，零样本迁移至厨房视频并达到与1B参数场景模型相近的性能。
摘要：
从操作视频中恢复自我相机朝向是从自我中心演示中分离手部运动与相机运动的前提，这是模仿学习的关键步骤。从场景几何推断朝向的常规方法在手部遮挡框架时失效：VGGT，一个1B参数的场景重建模型，在TACO基准测试上的表现甚至不如常数预测器。我们识别出一个替代的视觉概念，它恰好出现在场景几何缺失时：运动耦合动力学，即由手臂-肩-头链施加的手腕运动与相机朝向之间的结构化物理关系。我们发现这个概念是紧凑的（4D手腕间特征优于126D全手关键点）、时序的（需要短窗口上的GRU而非逐帧检索）和物理基础的（由于根植于解剖学而非场景外观，因此可零样本跨数据集迁移）。仅在桌面操作上训练的WristCompass，零样本迁移至Epic Kitchens烹饪视频，实现了14.3°的中位测地误差，并以200K GRU参数接近1B参数场景模型的性能。
英文摘要：
Recovering ego-camera orientation from manipulation video is a prerequisite for disentangling hand motion from camera motion, a key step in imitation learning from egocentric demonstrations. The obvious approach, inferring orientation from scene geometry, fails when hands occlude the frame: VGGT, a 1B-parameter scene reconstruction model, scores worse than a constant predictor on the TACO benchmark. We identify an alternative visual concept that is present precisely when scene geometry is absent: kinematic coupling dynamics, the structured physical relationship between wrist motion and camera orientation imposed by the arm-shoulder-head chain. We find that this concept is compact (4D inter-wrist features outperform 126D full hand keypoints), temporal (requiring a GRU over short windows rather than per-frame retrieval), and physically grounded (transferring zero-shot across datasets because it is rooted in anatomy rather than scene appearance). Trained only on tabletop manipulation, WristCompass transfers zero-shot to Epic Kitchens cooking video, achieving 14.3$^\circ$ median geodesic error and approaching the performance of a 1B-parameter scene model at 200K GRU parameters.
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。
