World-Grounded Human Motion Recovery via Gravity-View Coordinates
This solves the issue of ambiguous world coordinate systems in human motion recovery for applications like robotics and AR/VR, though it is an incremental improvement over existing methods.
The paper tackles the problem of recovering world-grounded human motion from monocular video by addressing ambiguity in world coordinate definitions, resulting in a method that outperforms state-of-the-art in accuracy and speed on in-the-wild benchmarks.
We present a novel method for recovering world-grounded human motion from monocular video. The main challenge lies in the ambiguity of defining the world coordinate system, which varies between sequences. Previous approaches attempt to alleviate this issue by predicting relative motion in an autoregressive manner, but are prone to accumulating errors. Instead, we propose estimating human poses in a novel Gravity-View (GV) coordinate system, which is defined by the world gravity and the camera view direction. The proposed GV system is naturally gravity-aligned and uniquely defined for each video frame, largely reducing the ambiguity of learning image-pose mapping. The estimated poses can be transformed back to the world coordinate system using camera rotations, forming a global motion sequence. Additionally, the per-frame estimation avoids error accumulation in the autoregressive methods. Experiments on in-the-wild benchmarks demonstrate that our method recovers more realistic motion in both the camera space and world-grounded settings, outperforming state-of-the-art methods in both accuracy and speed. The code is available at https://zju3dv.github.io/gvhmr/.