Recovering Physically Plausible Human-Object Interactions from Monocular Videos
For researchers in 3D human-object interaction reconstruction, this method addresses the persistent problem of physical implausibility (interpenetration, floating) in kinematic-only approaches.
RePHO reconstructs physically plausible human-object interactions from monocular videos by combining kinematic estimation with reinforcement learning, achieving clear improvements in physical plausibility metrics over state-of-the-art methods on two benchmarks.
In this paper, we propose RePHO, a method to reconstruct physically plausible human-object interactions (HOI) from monocular videos. While existing kinematic-based approaches produce visually plausible motion, they often result in physically implausible artifacts such as interpenetration and object floating. To overcome these issues, we introduce a physics-guided reconstruction framework. We begin with a kinematic estimate and then refine it by training a policy with reinforcement learning (RL). This policy is optimized to reproduce the interaction in a physics simulator. Because kinematic estimates are typically noisy, naive RL training can fail. Therefore, we propose an adaptive sampling strategy with a dual self-updating mechanism that can identify the frames with the most informative and reliable kinematic reconstruction. Our process progressively improves reconstruction quality and yields physically consistent HOI sequences. We demonstrate our approach on two standard HOI benchmarks and achieve clear improvements in physical plausibility metrics over state-of-the-art methods. Project Page: https://dingbang777.github.io/RePHO/