MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915588456054784 |
|---|---|
| author | Gao, Jingnan Wang, Zhe Fang, Xianze Ren, Xingyu Chen, Zhuo Liu, Shengqi Cheng, Yuhao Lyu, Jiangjing Yang, Xiaokang Yan, Yichao |
| author_facet | Gao, Jingnan Wang, Zhe Fang, Xianze Ren, Xingyu Chen, Zhuo Liu, Shengqi Cheng, Yuhao Lyu, Jiangjing Yang, Xiaokang Yan, Yichao |
| contents | Recent advances in language and vision have demonstrated that scaling up model capacity consistently improves performance across diverse tasks. In 3D visual geometry reconstruction, large-scale training has likewise proven effective for learning versatile representations. However, further scaling of 3D models is challenging due to the complexity of geometric supervision and the diversity of 3D data. To overcome these limitations, we propose MoRE, a dense 3D visual foundation model based on a Mixture-of-Experts (MoE) architecture that dynamically routes features to task-specific experts, allowing them to specialize in complementary data aspects and enhance both scalability and adaptability. Aiming to improve robustness under real-world conditions, MoRE incorporates a confidence-based depth refinement module that stabilizes and refines geometric estimation. In addition, it integrates dense semantic features with globally aligned 3D backbone representations for high-fidelity surface normal prediction. MoRE is further optimized with tailored loss functions to ensure robust learning across diverse inputs and multiple geometric tasks. Extensive experiments demonstrate that MoRE achieves state-of-the-art performance across multiple benchmarks and supports effective downstream applications without extra computation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_27234 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts Gao, Jingnan Wang, Zhe Fang, Xianze Ren, Xingyu Chen, Zhuo Liu, Shengqi Cheng, Yuhao Lyu, Jiangjing Yang, Xiaokang Yan, Yichao Computer Vision and Pattern Recognition Recent advances in language and vision have demonstrated that scaling up model capacity consistently improves performance across diverse tasks. In 3D visual geometry reconstruction, large-scale training has likewise proven effective for learning versatile representations. However, further scaling of 3D models is challenging due to the complexity of geometric supervision and the diversity of 3D data. To overcome these limitations, we propose MoRE, a dense 3D visual foundation model based on a Mixture-of-Experts (MoE) architecture that dynamically routes features to task-specific experts, allowing them to specialize in complementary data aspects and enhance both scalability and adaptability. Aiming to improve robustness under real-world conditions, MoRE incorporates a confidence-based depth refinement module that stabilizes and refines geometric estimation. In addition, it integrates dense semantic features with globally aligned 3D backbone representations for high-fidelity surface normal prediction. MoRE is further optimized with tailored loss functions to ensure robust learning across diverse inputs and multiple geometric tasks. Extensive experiments demonstrate that MoRE achieves state-of-the-art performance across multiple benchmarks and supports effective downstream applications without extra computation. |
| title | MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.27234 |