Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation
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_ | 1866909539884859392 |
|---|---|
| author | Lian, Xinyu Yu, Zichao Liang, Ruiming Wang, Yitong Luo, Li Ray Chen, Kaixu Zhou, Yuanzhen Tang, Qihong Xu, Xudong Lyu, Zhaoyang Dai, Bo Pang, Jiangmiao |
| author_facet | Lian, Xinyu Yu, Zichao Liang, Ruiming Wang, Yitong Luo, Li Ray Chen, Kaixu Zhou, Yuanzhen Tang, Qihong Xu, Xudong Lyu, Zhaoyang Dai, Bo Pang, Jiangmiao |
| contents | Large-scale articulated objects with high quality are desperately needed for multiple tasks related to embodied AI. Most existing methods for creating articulated objects are either data-driven or simulation based, which are limited by the scale and quality of the training data or the fidelity and heavy labour of the simulation. In this paper, we propose Infinite Mobility, a novel method for synthesizing high-fidelity articulated objects through procedural generation. User study and quantitative evaluation demonstrate that our method can produce results that excel current state-of-the-art methods and are comparable to human-annotated datasets in both physics property and mesh quality. Furthermore, we show that our synthetic data can be used as training data for generative models, enabling next-step scaling up. Code is available at https://github.com/Intern-Nexus/Infinite-Mobility |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13424 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation Lian, Xinyu Yu, Zichao Liang, Ruiming Wang, Yitong Luo, Li Ray Chen, Kaixu Zhou, Yuanzhen Tang, Qihong Xu, Xudong Lyu, Zhaoyang Dai, Bo Pang, Jiangmiao Computer Vision and Pattern Recognition Large-scale articulated objects with high quality are desperately needed for multiple tasks related to embodied AI. Most existing methods for creating articulated objects are either data-driven or simulation based, which are limited by the scale and quality of the training data or the fidelity and heavy labour of the simulation. In this paper, we propose Infinite Mobility, a novel method for synthesizing high-fidelity articulated objects through procedural generation. User study and quantitative evaluation demonstrate that our method can produce results that excel current state-of-the-art methods and are comparable to human-annotated datasets in both physics property and mesh quality. Furthermore, we show that our synthetic data can be used as training data for generative models, enabling next-step scaling up. Code is available at https://github.com/Intern-Nexus/Infinite-Mobility |
| title | Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.13424 |