H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911310947549184 |
|---|---|
| author | Ci, Hai Liu, Xiaokang Yang, Pei Song, Yiren Shou, Mike Zheng |
| author_facet | Ci, Hai Liu, Xiaokang Yang, Pei Song, Yiren Shou, Mike Zheng |
| contents | Robots that learn manipulation skills from everyday human videos could acquire broad capabilities without tedious robot data collection. We propose a video-to-video translation framework that converts ordinary human-object interaction videos into motion-consistent robot manipulation videos with realistic, physically grounded interactions. Our approach does not require any paired human-robot videos for training only a set of unpaired robot videos, making the system easy to scale. We introduce a transferable representation that bridges the embodiment gap: by inpainting the robot arm in training videos to obtain a clean background and overlaying a simple visual cue (a marker and arrow indicating the gripper's position and orientation), we can condition a generative model to insert the robot arm back into the scene. At test time, we apply the same process to human videos (inpainting the person and overlaying human pose cues) and generate high-quality robot videos that mimic the human's actions. We fine-tune a SOTA video diffusion model (Wan 2.2) in an in-context learning manner to ensure temporal coherence and leveraging of its rich prior knowledge. Empirical results demonstrate that our approach achieves significantly more realistic and grounded robot motions compared to baselines, pointing to a promising direction for scaling up robot learning from unlabeled human videos. Project page: https://showlab.github.io/H2R-Grounder/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09406 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos Ci, Hai Liu, Xiaokang Yang, Pei Song, Yiren Shou, Mike Zheng Robotics Artificial Intelligence Computer Vision and Pattern Recognition Robots that learn manipulation skills from everyday human videos could acquire broad capabilities without tedious robot data collection. We propose a video-to-video translation framework that converts ordinary human-object interaction videos into motion-consistent robot manipulation videos with realistic, physically grounded interactions. Our approach does not require any paired human-robot videos for training only a set of unpaired robot videos, making the system easy to scale. We introduce a transferable representation that bridges the embodiment gap: by inpainting the robot arm in training videos to obtain a clean background and overlaying a simple visual cue (a marker and arrow indicating the gripper's position and orientation), we can condition a generative model to insert the robot arm back into the scene. At test time, we apply the same process to human videos (inpainting the person and overlaying human pose cues) and generate high-quality robot videos that mimic the human's actions. We fine-tune a SOTA video diffusion model (Wan 2.2) in an in-context learning manner to ensure temporal coherence and leveraging of its rich prior knowledge. Empirical results demonstrate that our approach achieves significantly more realistic and grounded robot motions compared to baselines, pointing to a promising direction for scaling up robot learning from unlabeled human videos. Project page: https://showlab.github.io/H2R-Grounder/ |
| title | H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.09406 |