Research map / 3D vision / Depth and stereo
PoGO-Net: Pose Graph Optimization With Graph Neural Networks
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 |
|---|---|---|---|
| use PoGO-Net instead of NeuRoRA (end-to-end GNN with de-noise layers) | NeuRoRA · ScanNet | mean angular error: 11.02 -> 8.22 | Improved |
| use PoGO-Net instead of NeuRoRA | NeuRoRA · ScanNet | median angular error: 6.92 -> 3.04 | Improved |
| use PoGO-Net instead of CNN+GNN | CNN+GNN · 7Scenes average | angular error: 6.33 -> 4.93 | Improved |
| use PoGO-Net instead of RelocNet on Stairs | RelocNet · 7Scenes Stairs | angular error: 7.53 -> 7.88 | Hurt |
| use PoGO-Net instead of CNN+GNN on Pumpkin | CNN+GNN · 7Scenes Pumpkin | angular error: 2.77 -> 3.56 | Hurt |
| train PoGO-Net on Cambridge itself instead of on 7Scenes | PoGO-Net · Cambridge average | angular error: 8.29 -> 3.47 | Improved |
| train PoGO-Net on Photo Tourism instead of ScanNet, tested on Cambridge | PoGO-Net · Cambridge average | angular error: 6.65 -> 5.04 | Improved |
| add more de-noise layers (30%, 50%, full) (ablation) | PoGO-Net · 7Scenes with added edge noise | median angular error | Improved |
| use PoGO-Net trained on Cambridge instead of PoseNet17 | PoseNet17 · Cambridge average | angular error: 5.03 -> 3.47 | 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
- Learning Global Camera Poses from Noisy View-Graphs for Structure from Motion (ECCV 2026 · similarity 0.89)
- Learning Multi-View Camera Relocalization With Graph Neural Networks (CVPR 2020 · similarity 0.88)
- Learning to Filter Outlier Edges in Global SfM (CVPR 2025 · similarity 0.88)
- Learning Structure-from-Motion with Graph Attention Networks (CVPR 2024 · similarity 0.85)
- Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization (CVPR 2025 · similarity 0.85)
- Map-Relative Pose Regression for Visual Re-Localization (CVPR 2024 · 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.
