Research map / Graph learning / Graph algorithms and clustering
Learning To Bundle-Adjust: A Graph Network Approach to Faster Optimization of Bundle Adjustment for Vehicular SLAM
Tetsuya Tanaka, Yukihiro Sasagawa, Takayuki Okatani
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 |
|---|---|---|---|
| replace g2o Levenberg-Marquardt BA with the learned graph network in local BA | OpenVSLAM · KITTI local BA runs | Time per BA run (sec): 0.2 -> 0.003 | Improved |
| replace g2o BA with the learned graph network in full SLAM | OpenVSLAM · KITTI K07 (full SLAM) | Time per BA run (sec): 0.2 -> 0.04 | Improved |
| replace g2o BA with the learned graph network in full SLAM | OpenVSLAM · KITTI K07 (full SLAM) | Absolute trajectory RMSE (m): 8.26 -> 11.90 | Hurt |
| increase the number of stacked GN blocks S up to 4, then to 5 (ablation) | Graph network BA · KITTI local BA runs | Residual Huber loss | Mixed |
| use the learned BA instead of g2o on individual BA runs | OpenVSLAM · KITTI local BA runs | Residual Huber loss | Hurt |
Closest papers by meaning
- ICE-BA: Incremental, Consistent and Efficient Bundle Adjustment for Visual-Inertial SLAM (CVPR 2018 · similarity 0.86)
- A Game of Bundle Adjustment - Learning Efficient Convergence (ICCV 2023 · similarity 0.86)
- Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction (ECCV 2020 · similarity 0.86)
- Bundle Adjustment on a Graph Processor (CVPR 2020 · similarity 0.86)
- Learning Structure-from-Motion with Graph Attention Networks (CVPR 2024 · similarity 0.85)
- From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers (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.
