Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.30342 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913170842451968 |
|---|---|
| author | Xue, Shangjie Dill, Jesse Ahuja, Dhruv Dellaert, Frank Tsiotras, Panagiotis Xu, Danfei |
| author_facet | Xue, Shangjie Dill, Jesse Ahuja, Dhruv Dellaert, Frank Tsiotras, Panagiotis Xu, Danfei |
| contents | We present Gaussian Splatting Anisotropic Visibility Field (GAVIS), a novel framework for uncertainty quantification and active mapping in 3DGS. Our key insight is that regions unseen from the training views yield unreliable predictions from the 3DGS. To address this, we introduce a principled and efficient method for quantifying the visibility field in 3DGS, defined as the anisotropic visibility of each particle with respect to the training views, and represented using spherical harmonics. The resulting visibility field is integrated into a Bayesian Network-based uncertainty-aware 3DGS rasterizer, enabling real-time (200 FPS) uncertainty quantification for synthesized views. Active mapping is further performed within a maximum information gain framework building on this formulation. Extensive experiments across diverse environments demonstrate that GAVIS consistently and significantly outperforms prior approaches in both accuracy and efficiency. Moreover, beyond standalone use, our method can be applied post-hoc to improve the performance of existing approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30342 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field Xue, Shangjie Dill, Jesse Ahuja, Dhruv Dellaert, Frank Tsiotras, Panagiotis Xu, Danfei Computer Vision and Pattern Recognition Robotics We present Gaussian Splatting Anisotropic Visibility Field (GAVIS), a novel framework for uncertainty quantification and active mapping in 3DGS. Our key insight is that regions unseen from the training views yield unreliable predictions from the 3DGS. To address this, we introduce a principled and efficient method for quantifying the visibility field in 3DGS, defined as the anisotropic visibility of each particle with respect to the training views, and represented using spherical harmonics. The resulting visibility field is integrated into a Bayesian Network-based uncertainty-aware 3DGS rasterizer, enabling real-time (200 FPS) uncertainty quantification for synthesized views. Active mapping is further performed within a maximum information gain framework building on this formulation. Extensive experiments across diverse environments demonstrate that GAVIS consistently and significantly outperforms prior approaches in both accuracy and efficiency. Moreover, beyond standalone use, our method can be applied post-hoc to improve the performance of existing approaches. |
| title | Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2605.30342 |