Research map / 3D vision / Depth and stereo
On-The-Fly Adaptation of Regression Forests for Online Camera Relocalisation
Tommaso Cavallari, Stuart Golodetz, Nicholas A. Lord, Julien Valentin, Luigi Di Stefano, Philip H. S. Torr
Check 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 ICP pose refinement (ablation) | adapted regression forest · 7-Scenes average across training scenes | relocalisation success: 80.9% -> 84.9% | Improved |
| adapt a generic-scene forest online by refilling its leaves with target-scene examples | regression forest camera relocaliser · 7-Scenes average | relocalisation success: 84.6% vs 89.5% | Mixed |
| use ICP refinement after adaptation (ablation) | adapted regression forest · 7-Scenes | relocalisation success: 84.6% -> 87.1% | Improved |
| use the adapted forest instead of keyframe-based random ferns | online camera relocalisation · 7-Scenes / relocalisation | relocalisation time: 10ms -> 141ms | Hurt |
| use the adapted forest instead of random ferns | online training · per-frame training | per-frame training time: 0.9ms -> 9.8ms | Hurt |
| use the adapted forest rather than keyframe-based random ferns | novel-pose camera relocalisation · 7-Scenes, test poses increasingly distant from training trajectory | relocalisation success | Improved |
Closest papers by meaning
- Real-Time RGB-D Camera Pose Estimation in Novel Scenes Using a Relocalisation Cascade (TPAMI 2019 · similarity 0.95)
- Accelerated Coordinate Encoding: Learning to Relocalize in Minutes Using RGB and Poses (CVPR 2023 · similarity 0.87)
- On the Limits of Pseudo Ground Truth in Visual Camera Re-Localisation (ICCV 2021 · similarity 0.87)
- Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer (ECCV 2024 · similarity 0.86)
- Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments (CVPR 2024 · similarity 0.86)
- Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization (CVPR 2025 · similarity 0.85)
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.
