Research map / 3D vision / Depth and stereo
Generalizing to the Open World: Deep Visual Odometry With Online Adaptation
Shunkai Li, Xin Wu, Yingdian Cao, Hongbin Zha
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 |
|---|---|---|---|
| Use online adaptation with Bayesian-refined depth and geometric pose recovery | Deep visual odometry pretrained on Cityscapes · KITTI odometry Seq.00 | translation RMSE drift (%): 2.25 -> 1.32 | Improved |
| Use online adaptation with Bayesian-refined depth and geometric pose recovery | Deep visual odometry pretrained on KITTI · TUM-RGBD fr2/desk | translational RPE RMSE (m/s): 0.306 -> 0.158 | Improved |
| Use triangulation and Bayesian updating for depth learning | Single-view depth estimation · KITTI Eigen split | Abs Rel: 0.113 -> 0.106 | Improved |
| Add refined depth for online supervision of DepthNet and FlowNet (ablation) | Deep visual odometry · KITTI odometry Seq.00 | translation RMSE drift (%): 4.67 -> 1.32 | Improved |
| Add refined depth for online supervision of DepthNet and FlowNet (ablation) | Deep visual odometry · TUM-RGBD fr2/desk | translational RPE RMSE (m/s): 0.572 -> 0.158 | Improved |
| Add refined depth for online supervision (ablation) | Single-view depth estimation · KITTI Eigen split | Abs Rel: 0.136 -> 0.106 | Improved |
| Add refined depth for online supervision (ablation) | Single-view depth estimation · NYUv2 | Rel: 0.225 -> 0.139 | Improved |
| Add online learned photometric uncertainty (ablation) | Deep visual odometry · KITTI odometry Seq.00 | translation RMSE drift (%): 2.28 -> 1.32 | Improved |
| Add online learned photometric uncertainty (ablation) | Deep visual odometry · TUM-RGBD fr2/desk | translational RPE RMSE (m/s): 0.221 -> 0.158 | Improved |
| Add online learned photometric uncertainty (ablation) | Single-view depth estimation · KITTI Eigen split | Abs Rel: 0.115 -> 0.106 | Improved |
| Add online learned photometric uncertainty (ablation) | Single-view depth estimation · NYUv2 | Rel: 0.142 -> 0.139 | Improved |
Closest papers by meaning
- Self-Supervised Deep Visual Odometry With Online Adaptation (CVPR 2020 · similarity 0.92)
- Deep Visual Odometry With Adaptive Memory (TPAMI 2020 · similarity 0.90)
- Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning (CVPR 2024 · similarity 0.89)
- ZeroVO: Visual Odometry with Minimal Assumptions (CVPR 2025 · similarity 0.87)
- Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry (AAAI 2025 · similarity 0.87)
- LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry (CVPR 2024 · similarity 0.87)
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.
