Physics-aware Hand-object Interaction Denoising
This work addresses the challenge of high occlusions in vision-based hand tracking for applications like robotics and VR, though it is incremental as it builds on existing trackers.
The paper tackled the problem of physical plausibility in hand-object interaction sequences by proposing a physics-aware denoising method, which significantly improved both physical plausibility and pose accuracy over state-of-the-art methods.
The credibility and practicality of a reconstructed hand-object interaction sequence depend largely on its physical plausibility. However, due to high occlusions during hand-object interaction, physical plausibility remains a challenging criterion for purely vision-based tracking methods. To address this issue and enhance the results of existing hand trackers, this paper proposes a novel physically-aware hand motion de-noising method. Specifically, we introduce two learned loss terms that explicitly capture two crucial aspects of physical plausibility: grasp credibility and manipulation feasibility. These terms are used to train a physically-aware de-noising network. Qualitative and quantitative experiments demonstrate that our approach significantly improves both fine-grained physical plausibility and overall pose accuracy, surpassing current state-of-the-art de-noising methods.