# DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation

arXiv: https://arxiv.org/abs/2604.20841 · HTML: https://mlsanity.com/paper/2604.20841/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 59 of its 71 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Builds on (most cited first, 30 of 59)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [Learning Universal Policies via Text-Guided Video Generation](https://mlsanity.com/paper/2302.00111/) (2023)
- [InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models](https://mlsanity.com/paper/2404.07191/) (2024)
- [GRAB: A Dataset of Whole-Body Human Grasping of Objects](https://mlsanity.com/paper/2008.11200/) (2020)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation](https://mlsanity.com/paper/2204.13662/) (2022)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)
- [Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors](https://mlsanity.com/paper/2105.01859/) (2021)
- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [Object Motion Guided Human Motion Synthesis](https://mlsanity.com/paper/2309.16237/) (2023)
- [Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild](https://mlsanity.com/paper/2007.15649/) (2020)
- [World-Grounded Human Motion Recovery via Gravity-View Coordinates](https://mlsanity.com/paper/2409.06662/) (2024)
- [Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning](https://mlsanity.com/paper/2304.13653/) (2023)
- [ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills](https://mlsanity.com/paper/2502.01143/) (2025)
- [Universal Humanoid Motion Representations for Physics-Based Control](https://mlsanity.com/paper/2310.04582/) (2023)
- [MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting](https://mlsanity.com/paper/2409.14393/) (2024)
- [Controllable Human-Object Interaction Synthesis](https://mlsanity.com/paper/2312.03913/) (2023)
- [CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control](https://mlsanity.com/paper/2410.03441/) (2024)

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

- [SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image](https://mlsanity.com/paper/2606.03994/) (2026)

## Abstract (arXiv)

Physics-based character control for dexterous Human-Object Interaction (HOI) relies heavily on motion-capture data, which limits its applicability beyond captured scenarios. Meanwhile, video generative models can synthesize realistic HOI videos for unseen objects and scenarios directly from text prompts, but 3D interactions learned from such synthetic data remain kinematic without ensuring physical plausibility. Imitating these videos with physics-based control is a promising direction, yet unreliable object tracking and hand-object misalignment make it difficult to obtain accurate imitation targets. We present DeVI (Dexterous Video Imitation), a novel framework that learns physics-based character control for dexterous HOI by imitating text-conditioned synthetic videos. To address unreliable 3D object motion reconstruction, we introduce hybrid imitation targets that combine reconstructed 3D human motion with tracked 2D object trajectories, bypassing the explicit reconstruction of the 3D object motion. Our Visual HOI Alignment further refines the human reference to align with both the generated video and the initial 3D object configuration, making it suitable for physical interaction. Extensive experiments show that DeVI's hybrid representation is more effective than those used by the baselines and that Visual HOI Alignment improves reconstruction quality and imitation success. We further demonstrate physically plausible functional manipulation from text instructions, including target-aware interactions and articulated object manipulation, without requiring motion-capture demonstrations.