# MotionGRPO: Overcoming Low Intra-Group Diversity in GRPO-Based Egocentric Motion Recovery

arXiv: https://arxiv.org/abs/2605.05680 · HTML: https://mlsanity.com/paper/2605.05680/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 59 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [Project Aria: A New Tool for Egocentric Multi-Modal AI Research](https://mlsanity.com/paper/2308.13561/) (2023)
- [Capturing and Inferring Dense Full-Body Human-Scene Contact](https://mlsanity.com/paper/2206.09553/) (2022)
- [Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception](https://mlsanity.com/paper/2306.06362/) (2023)
- [AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing](https://mlsanity.com/paper/2207.13784/) (2022)
- [Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model](https://mlsanity.com/paper/2304.08577/) (2023)
- [Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation](https://mlsanity.com/paper/2106.05969/) (2021)
- [Ego-Body Pose Estimation via Ego-Head Pose Estimation](https://mlsanity.com/paper/2212.04636/) (2022)
- [Ego-Pose Estimation and Forecasting as Real-Time PD Control](https://mlsanity.com/paper/1906.03173/) (2019)
- [Estimating Body and Hand Motion in an Ego-sensed World](https://mlsanity.com/paper/2410.03665/) (2024)
- [IDOL: Instant Photorealistic 3D Human Creation from a Single Image](https://mlsanity.com/paper/2412.14963/) (2024)
- [EgoLocate: Real-time Motion Capture, Localization, and Mapping with Sparse Body-mounted Sensors](https://mlsanity.com/paper/2305.01599/) (2023)

## Built on by (most cited first, 1 of 1)

- [FlowHMR: Physically Plausible Motion Capture from Video](https://mlsanity.com/paper/2610.03691/) (2026)

## Abstract (arXiv)

This paper studies full-body 3D human motion recovery from head-mounted device signals. Existing diffusion-based methods often rely on global distribution matching, leading to local joint reconstruction errors. We propose MotionGRPO, a novel framework leveraging reinforcement learning post-training to inject fine-grained guidance into the diffusion process. Technically, we model diffusion sampling as a Markov decision process optimized via Group Relative Policy Optimization (GRPO). To this end, we introduce a hybrid reward mechanism that combines a learned conditioned perceptual model for global visual plausibility and explicit constraints for local joint precision. Our key technical insight is that policy optimization in diffusion-based recovery suffers from vanishing gradients due to limited intra-group sample diversity. To address this, we further introduce a noise-injection strategy that explicitly increases sample variance and stabilizes learning. Extensive experiments demonstrate that MotionGRPO achieves state-of-the-art performance with superior visual fidelity