Research map / 3D vision / Gaussian splatting
Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field
Shangjie Xue, Jesse Dill, Dhruv Ahuja, Frank Dellaert, Panagiotis Tsiotras, Danfei Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add anisotropic (directional) visibility (ablation) | GAVIS · All datasets average (ablation) | PSNR: 23.97 -> 24.70 | Improved |
| add anisotropic (directional) visibility (ablation) | GAVIS · All datasets average (ablation) | VIS: 0.671 -> 0.697 | Improved |
| add visibility field density control (virtual particles) (ablation) | GAVIS · All datasets average (ablation) | PSNR: 24.18 -> 24.70 | Improved |
| add visibility field density control (virtual particles) (ablation) | GAVIS · All datasets average (ablation) | CR: 0.712 -> 0.748 | Improved |
| add both anisotropy and density control (ablation) | GAVIS · All datasets average (ablation) | PSNR: 23.38 -> 24.70 | Improved |
| apply GAVIS post hoc to FisherRF | FisherRF · All datasets average (post-hoc) | PSNR: 20.73 -> 24.70 | Improved |
| apply GAVIS post hoc to VIMC | VIMC · All datasets average (post-hoc) | PSNR: 20.14 -> 24.21 | Improved |
| add FisherRF variance to GAVIS | GAVIS · All datasets average (post-hoc) | PSNR: 24.70 -> 24.70 | No clear effect |
| add VIMC variance to GAVIS | GAVIS · All datasets average (post-hoc) | PSNR: 24.70 -> 24.21 | Hurt |
| use GAVIS instead of NVF | NVF · NeRF Synthetic | T_UP: 149.13 -> 0.17 | Improved |
| use GAVIS instead of NVF | NVF · Gibson | CR: 0.880 -> 0.831 | Hurt |
| use GAVIS instead of NVF | NVF · Gibson | PSNR: 23.29 -> 24.42 | Improved |
Closest papers by meaning
- Variational Multi-scale Representation for Estimating Uncertainty in 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.92)
- ActiveGAMER: Active GAussian Mapping through Efficient Rendering (CVPR 2025 · similarity 0.89)
- POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimality (CVPR 2025 · similarity 0.89)
- UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mapping (CVPR 2025 · similarity 0.89)
- Metropolis-Hastings Sampling for 3D Gaussian Reconstruction (NeurIPS 2025 · similarity 0.88)
- Volumetrically Consistent 3D Gaussian Rasterization (CVPR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
