Research map / Label-efficient and robust learning / Self-supervised and contrastive
Self-Supervised Deep Visual Odometry With Online Adaptation
Shunkai Li, Xin Wang, Yingdian Cao, Fei Xue, Zike Yan, 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 next-window loss after an inner-loop update (meta-learning) instead of naive online learning (ablation) | Self-supervised VO · KITTI Seq. 09 | t_err (%): 10.22 -> 5.89 | Improved |
| use next-window loss after an inner-loop update (meta-learning) instead of naive online learning (ablation) | Self-supervised VO · KITTI Seq. 10 | t_err (%): 8.24 -> 4.79 | Improved |
| add convLSTM to meta-learning (ablation) | Self-supervised VO · KITTI Seq. 09 | t_err (%): 9.25 -> 6.36 | Improved |
| add convLSTM to meta-learning (ablation) | Self-supervised VO · KITTI Seq. 10 | t_err (%): 7.58 -> 5.37 | Improved |
| add feature alignment to meta-learning (ablation) | Self-supervised VO · KITTI Seq. 09 | t_err (%): 9.25 -> 7.52 | Improved |
| add feature alignment to meta-learning (ablation) | Self-supervised VO · KITTI Seq. 10 | t_err (%): 7.58 -> 5.98 | Improved |
| add convLSTM to meta-learning with feature alignment (ablation) | Self-supervised VO · KITTI Seq. 09 | t_err (%): 7.52 -> 5.89 | Improved |
| add convLSTM to meta-learning with feature alignment (ablation) | Self-supervised VO · KITTI Seq. 10 | t_err (%): 5.98 -> 4.79 | Improved |
| add feature alignment to meta-learning with convLSTM (ablation) | Self-supervised VO · KITTI Seq. 09 | t_err (%): 6.36 -> 5.89 | Improved |
| add feature alignment to meta-learning with convLSTM (ablation) | Self-supervised VO · KITTI Seq. 10 | t_err (%): 5.37 -> 4.79 | Improved |
| replace meta-learning with naive online learning (ablation) | Self-supervised VO with LSTM and feature alignment · KITTI Seq. 09 | r_err (°/100m): 3.34 -> 5.33 | Hurt |
| increase sliding-window length up to 15 frames (ablation) | Self-supervised VO · KITTI | adaptation speed and accuracy | Improved |
Closest papers by meaning
- Generalizing to the Open World: Deep Visual Odometry With Online Adaptation (CVPR 2021 · similarity 0.92)
- Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling (ECCV 2020 · similarity 0.90)
- Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry (ICCV 2019 · similarity 0.90)
- Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning (CVPR 2024 · similarity 0.86)
- Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry (AAAI 2025 · similarity 0.85)
- LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry (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.
