SIGHT: Synthesizing Image-Text Conditioned and Geometry-Guided 3D Hand-Object Trajectories
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913865715941376 |
|---|---|
| author | Gavryushin, Alexey Delitzas, Alexandros Van Gool, Luc Pollefeys, Marc Mo, Kaichun Wang, Xi |
| author_facet | Gavryushin, Alexey Delitzas, Alexandros Van Gool, Luc Pollefeys, Marc Mo, Kaichun Wang, Xi |
| contents | When humans grasp an object, they naturally form trajectories in their minds to manipulate it for specific tasks. Modeling hand-object interaction priors holds significant potential to advance robotic and embodied AI systems in learning to operate effectively within the physical world. We introduce SIGHT, a novel task focused on generating realistic and physically plausible 3D hand-object interaction trajectories from a single image and a brief language-based task description. Prior work on hand-object trajectory generation typically relies on textual input that lacks explicit grounding to the target object, or assumes access to 3D object meshes, which are often considerably more difficult to obtain than 2D images. We propose SIGHT-Fusion, a novel diffusion-based image-text conditioned generative model that tackles this task by retrieving the most similar 3D object mesh from a database and enforcing geometric hand-object interaction constraints via a novel inference-time diffusion guidance. We benchmark our model on the HOI4D and H2O datasets, adapting relevant baselines for this novel task. Experiments demonstrate our superior performance in the diversity and quality of generated trajectories, as well as in hand-object interaction geometry metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22869 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SIGHT: Synthesizing Image-Text Conditioned and Geometry-Guided 3D Hand-Object Trajectories Gavryushin, Alexey Delitzas, Alexandros Van Gool, Luc Pollefeys, Marc Mo, Kaichun Wang, Xi Computer Vision and Pattern Recognition When humans grasp an object, they naturally form trajectories in their minds to manipulate it for specific tasks. Modeling hand-object interaction priors holds significant potential to advance robotic and embodied AI systems in learning to operate effectively within the physical world. We introduce SIGHT, a novel task focused on generating realistic and physically plausible 3D hand-object interaction trajectories from a single image and a brief language-based task description. Prior work on hand-object trajectory generation typically relies on textual input that lacks explicit grounding to the target object, or assumes access to 3D object meshes, which are often considerably more difficult to obtain than 2D images. We propose SIGHT-Fusion, a novel diffusion-based image-text conditioned generative model that tackles this task by retrieving the most similar 3D object mesh from a database and enforcing geometric hand-object interaction constraints via a novel inference-time diffusion guidance. We benchmark our model on the HOI4D and H2O datasets, adapting relevant baselines for this novel task. Experiments demonstrate our superior performance in the diversity and quality of generated trajectories, as well as in hand-object interaction geometry metrics. |
| title | SIGHT: Synthesizing Image-Text Conditioned and Geometry-Guided 3D Hand-Object Trajectories |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.22869 |