Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917359362506752 |
|---|---|
| author | Galappaththige, Chamuditha Jayanga Gottwald, Thomas Stehr, Peter Heinert, Edgar Suenderhauf, Niko Miller, Dimity Rottmann, Matthias |
| author_facet | Galappaththige, Chamuditha Jayanga Gottwald, Thomas Stehr, Peter Heinert, Edgar Suenderhauf, Niko Miller, Dimity Rottmann, Matthias |
| contents | Recent advances in 3D Gaussian Splatting have enabled impressive photorealistic novel view synthesis. However, to transition from a pure rendering engine to a reliable spatial map for autonomous agents and safety-critical applications, knowing where the representation is uncertain is as important as the rendering fidelity itself. We bridge this critical gap by introducing a lightweight, plug-and-play framework for pixel-wise, view-dependent predictive uncertainty estimation. Our post-hoc method formulates uncertainty as a Bayesian-regularized linear least-squares optimization over reconstruction residuals. This architecture-agnostic approach extracts a per-primitive uncertainty channel without modifying the underlying scene representation or degrading baseline visual fidelity. Crucially, we demonstrate that providing this actionable reliability signal successfully translates 3D Gaussian splatting into a trustworthy spatial map, further improving state-of-the-art performance across three critical downstream perception tasks: active view selection, pose-agnostic scene change detection, and pose-agnostic anomaly detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_22786 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis Galappaththige, Chamuditha Jayanga Gottwald, Thomas Stehr, Peter Heinert, Edgar Suenderhauf, Niko Miller, Dimity Rottmann, Matthias Computer Vision and Pattern Recognition Recent advances in 3D Gaussian Splatting have enabled impressive photorealistic novel view synthesis. However, to transition from a pure rendering engine to a reliable spatial map for autonomous agents and safety-critical applications, knowing where the representation is uncertain is as important as the rendering fidelity itself. We bridge this critical gap by introducing a lightweight, plug-and-play framework for pixel-wise, view-dependent predictive uncertainty estimation. Our post-hoc method formulates uncertainty as a Bayesian-regularized linear least-squares optimization over reconstruction residuals. This architecture-agnostic approach extracts a per-primitive uncertainty channel without modifying the underlying scene representation or degrading baseline visual fidelity. Crucially, we demonstrate that providing this actionable reliability signal successfully translates 3D Gaussian splatting into a trustworthy spatial map, further improving state-of-the-art performance across three critical downstream perception tasks: active view selection, pose-agnostic scene change detection, and pose-agnostic anomaly detection. |
| title | Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.22786 |