人类即棋盘：面向世界坐标人体网格恢复的相机运动尺度校准
Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery
AI总结：
针对单目SLAM尺度未知导致全局人体运动恢复不准的问题，提出无需优化的HAC框架，以人体网格恢复模型预测的人体接触关节绝对深度校准SLAM尺度，实现高精度高效的全局人体网格估计。
摘要：
准确的相机运动估计对于从RGB视频输入中恢复世界坐标下的全局人体运动至关重要。SLAM（同时定位与地图构建）被广泛用于估计相机轨迹和点云，但单目SLAM的估计结果存在未知的尺度因子。以往研究通过优化估计尺度因子，但这种方法可靠性差且耗时。本文提出一种无需优化的尺度校准框架——Human as Checkerboard（HAC，人类即棋盘）。HAC创新性地将人体网格恢复模型预测的人体作为校准参考。具体而言，它利用人体-场景接触关节的绝对深度作为参考，校准SLAM输出的对应相对场景深度。HAC借助人体网格恢复模型中编码的几何先验来估计SLAM尺度，实现精准的全局人体运动估计。该方法简洁高效，在全局人体网格估计任务上创下新的最优性能，相比此前的局部到全局方法运动误差降低50%，同时推理时间比基于优化的方法少100倍。项目页面：https://martayang.github.io/HAC。
英文摘要：
Accurate camera motion estimation is essential for recovering global human motion in world coordinates from RGB video inputs. SLAM is widely used for estimating camera trajectory and point cloud, but monocular SLAM does so only up to an unknown scale factor. Previous works estimate the scale factor through optimization, but this is unreliable and time-consuming. This paper presents an optimization-free scale calibration framework, Human as Checkerboard (HAC). HAC innovatively leverages the human body predicted by human mesh recovery model as a calibration reference. Specifically, it uses the absolute depth of human-scene contact joints as references to calibrate the corresponding relative scene depth from SLAM. HAC benefits from geometric priors encoded in human mesh recovery models to estimate the SLAM scale and achieves precise global human motion estimation. Simple yet powerful, our method sets a new state-of-the-art performance for global human mesh estimation tasks, reducing motion errors by 50% over prior local-to-global methods while using 100$\times$ less inference time than optimization-based methods. Project page: https://martayang.github.io/HAC.
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。
