MARS: Mesh AutoRegressive Model for 3D Shape Detailization
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_ | 1866929717901262848 |
|---|---|
| author | Gao, Jingnan Liu, Weizhe Sun, Weixuan Wang, Senbo Song, Xibin Shang, Taizhang Chen, Shenzhou Li, Hongdong Yang, Xiaokang Yan, Yichao Ji, Pan |
| author_facet | Gao, Jingnan Liu, Weizhe Sun, Weixuan Wang, Senbo Song, Xibin Shang, Taizhang Chen, Shenzhou Li, Hongdong Yang, Xiaokang Yan, Yichao Ji, Pan |
| contents | State-of-the-art methods for mesh detailization predominantly utilize Generative Adversarial Networks (GANs) to generate detailed meshes from coarse ones. These methods typically learn a specific style code for each category or similar categories without enforcing geometry supervision across different Levels of Detail (LODs). Consequently, such methods often fail to generalize across a broader range of categories and cannot ensure shape consistency throughout the detailization process. In this paper, we introduce MARS, a novel approach for 3D shape detailization. Our method capitalizes on a novel multi-LOD, multi-category mesh representation to learn shape-consistent mesh representations in latent space across different LODs. We further propose a mesh autoregressive model capable of generating such latent representations through next-LOD token prediction. This approach significantly enhances the realism of the generated shapes. Extensive experiments conducted on the challenging 3D Shape Detailization benchmark demonstrate that our proposed MARS model achieves state-of-the-art performance, surpassing existing methods in both qualitative and quantitative assessments. Notably, the model's capability to generate fine-grained details while preserving the overall shape integrity is particularly commendable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_11390 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MARS: Mesh AutoRegressive Model for 3D Shape Detailization Gao, Jingnan Liu, Weizhe Sun, Weixuan Wang, Senbo Song, Xibin Shang, Taizhang Chen, Shenzhou Li, Hongdong Yang, Xiaokang Yan, Yichao Ji, Pan Computer Vision and Pattern Recognition State-of-the-art methods for mesh detailization predominantly utilize Generative Adversarial Networks (GANs) to generate detailed meshes from coarse ones. These methods typically learn a specific style code for each category or similar categories without enforcing geometry supervision across different Levels of Detail (LODs). Consequently, such methods often fail to generalize across a broader range of categories and cannot ensure shape consistency throughout the detailization process. In this paper, we introduce MARS, a novel approach for 3D shape detailization. Our method capitalizes on a novel multi-LOD, multi-category mesh representation to learn shape-consistent mesh representations in latent space across different LODs. We further propose a mesh autoregressive model capable of generating such latent representations through next-LOD token prediction. This approach significantly enhances the realism of the generated shapes. Extensive experiments conducted on the challenging 3D Shape Detailization benchmark demonstrate that our proposed MARS model achieves state-of-the-art performance, surpassing existing methods in both qualitative and quantitative assessments. Notably, the model's capability to generate fine-grained details while preserving the overall shape integrity is particularly commendable. |
| title | MARS: Mesh AutoRegressive Model for 3D Shape Detailization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.11390 |