Research map / 3D vision / Gaussian splatting
Scene Coordinate Reconstruction Priors
Wenjing Bian, Axel Barroso-Laguna, Tommaso Cavallari, Victor Adrian Prisacariu, Eric Brachmann
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 3D point cloud diffusion prior | ACE0 · Indoor6 SfM | registration rate: 57.1% -> 61.8% | Improved |
| add 3D point cloud diffusion prior | ACE0 · Indoor6 SfM | PSNR (dB): 13.5 -> 14.6 | Improved |
| add Laplace depth distribution prior (NLL) | ACE0 · Indoor6 SfM | registration rate: 57.1% -> 58.0% | Improved |
| use Wasserstein distance instead of NLL for depth prior | ACE0 · ScanNet 60/60 Splatfacto | PSNR (dB): 22.3 -> 21.7 | Hurt |
| add diffusion prior | ACE0 · ScanNet registration rate | registration rate: 98.1% -> 98.6% | Improved |
| add depth prior (Laplace NLL) with RGB-D input vs DSAC* loss | ACE0 · ScanNet RGB-D | registration rate: 96.2% -> 98.9% | Improved |
| add DSAC* loss throughout RGB-D reconstruction | ACE0 · ScanNet RGB-D | registration rate: 98.1% -> 96.2% | Hurt |
| add diffusion prior | ACE · 7Scenes | accuracy (%): 97.1% -> 97.7% | Improved |
| add diffusion prior | ACE · 7Scenes Stairs | accuracy (%): 81.9% -> 86.2% | Improved |
| add diffusion prior | ACE · Indoor6 (batch 51,200) | accuracy (%): 57.2% -> 57.9% | No clear effect |
| add diffusion prior | GLACE · Indoor6 (batch 51,200) | accuracy (%): 69.5% -> 69.6% | No clear effect |
| add diffusion prior | GLACE · 7Scenes | accuracy (%): 95.6% -> 95.9% | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- GLACE — GLACE: Global Local Accelerated Coordinate Encoding (CVPR 2024) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training (ICCV 2025 · similarity 0.91)
- Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer (ECCV 2024 · similarity 0.89)
- R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization (CVPR 2025 · similarity 0.88)
- GLACE: Global Local Accelerated Coordinate Encoding (CVPR 2024 · similarity 0.88)
- Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments (CVPR 2024 · similarity 0.87)
- Continuous 3D Perception Model with Persistent State (CVPR 2025 · similarity 0.86)
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.
