Recovering Physically Plausible Human-Object Interactions from Monocular Videos
Quick Answer
This paper shows that The RePHO method reconstructs physically plausible human-object interactions from monocular videos, overcoming common kinematic artifacts.
Quick Take
The RePHO method reconstructs physically plausible human-object interactions from monocular videos, overcoming common kinematic artifacts. By employing a physics-guided framework and reinforcement learning, it significantly improves interaction quality on standard benchmarks, outperforming state-of-the-art methods in physical plausibility metrics.
Key Points
- RePHO uses a physics-guided reconstruction framework to enhance human-object interactions.
- It employs reinforcement learning to refine kinematic estimates for better accuracy.
- An adaptive sampling strategy identifies the most reliable kinematic frames.
- The method shows significant improvements in physical plausibility over existing techniques.
- Demonstrated effectiveness on two standard human-object interaction benchmarks.
Article Excerpt
From source RSS / original summaryarXiv:2606. 05359v1 Announce Type: new Abstract: 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/
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.
