Towards Affordance-Aware Articulation Synthesis for Rigged Objects
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917898650386432 |
|---|---|
| author | Yu, Yu-Chu Lin, Chieh Hubert Lee, Hsin-Ying Wang, Chaoyang Wang, Yu-Chiang Frank Yang, Ming-Hsuan |
| author_facet | Yu, Yu-Chu Lin, Chieh Hubert Lee, Hsin-Ying Wang, Chaoyang Wang, Yu-Chiang Frank Yang, Ming-Hsuan |
| contents | Rigged objects are commonly used in artist pipelines, as they can flexibly adapt to different scenes and postures. However, articulating the rigs into realistic affordance-aware postures (e.g., following the context, respecting the physics and the personalities of the object) remains time-consuming and heavily relies on human labor from experienced artists. In this paper, we tackle the novel problem and design A3Syn. With a given context, such as the environment mesh and a text prompt of the desired posture, A3Syn synthesizes articulation parameters for arbitrary and open-domain rigged objects obtained from the Internet. The task is incredibly challenging due to the lack of training data, and we do not make any topological assumptions about the open-domain rigs. We propose using 2D inpainting diffusion model and several control techniques to synthesize in-context affordance information. Then, we develop an efficient bone correspondence alignment using a combination of differentiable rendering and semantic correspondence. A3Syn has stable convergence, completes in minutes, and synthesizes plausible affordance on different combinations of in-the-wild object rigs and scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_12393 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Affordance-Aware Articulation Synthesis for Rigged Objects Yu, Yu-Chu Lin, Chieh Hubert Lee, Hsin-Ying Wang, Chaoyang Wang, Yu-Chiang Frank Yang, Ming-Hsuan Computer Vision and Pattern Recognition Rigged objects are commonly used in artist pipelines, as they can flexibly adapt to different scenes and postures. However, articulating the rigs into realistic affordance-aware postures (e.g., following the context, respecting the physics and the personalities of the object) remains time-consuming and heavily relies on human labor from experienced artists. In this paper, we tackle the novel problem and design A3Syn. With a given context, such as the environment mesh and a text prompt of the desired posture, A3Syn synthesizes articulation parameters for arbitrary and open-domain rigged objects obtained from the Internet. The task is incredibly challenging due to the lack of training data, and we do not make any topological assumptions about the open-domain rigs. We propose using 2D inpainting diffusion model and several control techniques to synthesize in-context affordance information. Then, we develop an efficient bone correspondence alignment using a combination of differentiable rendering and semantic correspondence. A3Syn has stable convergence, completes in minutes, and synthesizes plausible affordance on different combinations of in-the-wild object rigs and scenes. |
| title | Towards Affordance-Aware Articulation Synthesis for Rigged Objects |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.12393 |