AI Paper Atlas

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

CVPR 2021 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 51 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use online adaptation with Bayesian-refined depth and geometric pose recoveryDeep visual odometry pretrained on Cityscapes · KITTI odometry Seq.00translation RMSE drift (%): 2.25 -> 1.32Improved
Use online adaptation with Bayesian-refined depth and geometric pose recoveryDeep visual odometry pretrained on KITTI · TUM-RGBD fr2/desktranslational RPE RMSE (m/s): 0.306 -> 0.158Improved
Use triangulation and Bayesian updating for depth learningSingle-view depth estimation · KITTI Eigen splitAbs Rel: 0.113 -> 0.106Improved
Add refined depth for online supervision of DepthNet and FlowNet (ablation)Deep visual odometry · KITTI odometry Seq.00translation RMSE drift (%): 4.67 -> 1.32Improved
Add refined depth for online supervision of DepthNet and FlowNet (ablation)Deep visual odometry · TUM-RGBD fr2/desktranslational RPE RMSE (m/s): 0.572 -> 0.158Improved
Add refined depth for online supervision (ablation)Single-view depth estimation · KITTI Eigen splitAbs Rel: 0.136 -> 0.106Improved
Add refined depth for online supervision (ablation)Single-view depth estimation · NYUv2Rel: 0.225 -> 0.139Improved
Add online learned photometric uncertainty (ablation)Deep visual odometry · KITTI odometry Seq.00translation RMSE drift (%): 2.28 -> 1.32Improved
Add online learned photometric uncertainty (ablation)Deep visual odometry · TUM-RGBD fr2/desktranslational RPE RMSE (m/s): 0.221 -> 0.158Improved
Add online learned photometric uncertainty (ablation)Single-view depth estimation · KITTI Eigen splitAbs Rel: 0.115 -> 0.106Improved
Add online learned photometric uncertainty (ablation)Single-view depth estimation · NYUv2Rel: 0.142 -> 0.139Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy