AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling

Yuliang Zou, Pan Ji, Quoc-Huy Tran, Jia-Bin Huang, Manmohan Chandraker

ECCV 2020 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 84 citations (OpenAlex)

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 changedWhereMeasuredEffect
add one-layer ConvLSTM to the pose network (ablation)pose network baseline · KITTI Odometry Seq 09relative translation error (%): 7.55 -> 5.59Improved
add one-layer ConvLSTM to the pose network (ablation)pose network baseline · KITTI Odometry Seq 10relative translation error (%): 10.43 -> 7.23Improved
add second ConvLSTM layer (ablation)one-layer ConvLSTM · KITTI Odometry Seq 09relative translation error (%): 5.59 -> 4.23Improved
add second ConvLSTM layer (ablation)one-layer ConvLSTM · KITTI Odometry Seq 10relative translation error (%): 7.23 -> 6.02Improved
add second-stage long-term training (ablation)two-layer ConvLSTM · KITTI Odometry Seq 09relative translation error (%): 4.23 -> 3.49Improved
add second-stage long-term training (ablation)two-layer ConvLSTM · KITTI Odometry Seq 10relative translation error (%): 6.02 -> 5.81Improved
add second-stage long-term training (ablation)two-layer ConvLSTM · KITTI Odometry Seq 09ATE RMSE (m): 9.77 -> 11.30Mixed
add cycle consistency constraint (ablation)two-layer ConvLSTM · KITTI Odometry Seq 09relative translation error (%): 5.02 -> 4.23Improved
add cycle consistency constraint (ablation)two-layer ConvLSTM · KITTI Odometry Seq 10relative translation error (%): 6.88 -> 6.02Improved
add pose features as input (ablation)two-layer ConvLSTM · KITTI Odometry Seq 09relative translation error (%): 5.64 -> 4.23Improved
add depth features as input (ablation)two-layer ConvLSTM · KITTI Odometry Seq 09relative translation error (%): 4.54 -> 4.23Improved
add memory buffer (ablation)two-layer ConvLSTM · KITTI Odometry Seq 09relative translation error (%): 5.12 -> 4.23Improved

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