Research map / 3D vision / Human pose estimation
GTCaR: Graph Transformer for Camera Re-Localization
Xinyi Li, Haibin Ling
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 graph Transformer layers (vs temporal only) (ablation) | GTCaR · Cambridge Court | median translation error (m): 6.95 -> 5.62 | Improved |
| add graph Transformer layers (vs temporal only) (ablation) | GTCaR · Oxford RobotCar LOOP | median translation error (m): 8.25 -> 5.46 | Improved |
| add graph Transformer layers (vs temporal only) (ablation) | GTCaR · 7-Scenes Pumpkin | median translation error (m): 0.31 -> 0.15 | Improved |
| add temporal Transformer layers (vs graph only) (ablation) | GTCaR · Cambridge Court | median translation error (m): 7.34 -> 5.62 | Improved |
| add temporal Transformer layers (vs graph only) (ablation) | GTCaR · Oxford RobotCar LOOP | median translation error (m): 9.03 -> 5.46 | Improved |
| add temporal Transformer layers (vs graph only) (ablation) | GTCaR · 7-Scenes Pumpkin | median translation error (m): 0.17 -> 0.15 | No clear effect |
| add MPNN layers with adjacency tensor (ablation) | GTCaR · Oxford RobotCar LOOP | median translation error (m): 7.95 -> 5.46 | Improved |
| add MPNN layers with adjacency tensor (ablation) | GTCaR · Cambridge Court | median translation error (m): 5.98 -> 5.62 | Improved |
| add MPNN layers with adjacency tensor (ablation) | GTCaR · 7-Scenes Pumpkin | median translation error (m): 0.20 -> 0.15 | Improved |
| use GTCaR graph Transformer instead of CNN+GNN | CNN+GNN · Oxford RobotCar LOOP | median translation error (m): 8.15 -> 5.46 | Improved |
| use GTCaR instead of CNN+GNN | CNN+GNN · Oxford RobotCar FULL | median rotation error (deg): 3.47 -> 3.68 | Hurt |
| use GTCaR instead of CNN+GNN | CNN+GNN · Cambridge (average of first four scenes) | median translation error (m): 1.12 -> 0.98 | 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.
- MapNet — MapNet: An Allocentric Spatial Memory for Mapping Environments (CVPR 2018) · better on 2 of 2 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
- PoGO-Net: Pose Graph Optimization With Graph Neural Networks (ICCV 2021 · similarity 0.88)
- Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization (CVPR 2025 · similarity 0.85)
- Learning to Filter Outlier Edges in Global SfM (CVPR 2025 · similarity 0.84)
- Scene-agnostic Pose Regression for Visual Localization (CVPR 2025 · similarity 0.84)
- ZeroVO: Visual Odometry with Minimal Assumptions (CVPR 2025 · similarity 0.84)
- GLACE: Global Local Accelerated Coordinate Encoding (CVPR 2024 · similarity 0.83)
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.
