AI Paper Atlas

Research map / Point clouds / Registration and matching

Efficient 3D Deep LiDAR Odometry

Guangming Wang, Xinrui Wu, Shuyang Jiang, Zhe Liu, Hesheng Wang

TPAMI 2022 · Point clouds › Registration and matching · approach: Learned feature-based registration · 69 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 the embedding mask (ablation)EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06)t_rel (%): 1.218 -> 0.795Improved
add hierarchical mask optimization (ablation)EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06)t_rel (%): 0.898 -> 0.795Improved
add pose warp-refinement module (ablation)EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06)t_rel (%): 3.76 -> 0.795Improved
add pose warping to hierarchical refinement (ablation)EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06)t_rel (%): 3.145 -> 0.795Improved
add the cost volume (ablation)EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06)t_rel (%): 11.790 -> 0.795Improved
use double attentive cost volume instead of point cost volume (ablation)EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06)t_rel (%): 0.870 -> 0.795Improved
first embedding at penultimate pyramid level instead of last level (ablation)EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06)t_rel (%): 1.153 -> 0.795Improved
keep ground points instead of removing ground below 0.55m (ablation)EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06)t_rel (%): 1.358 -> 0.795Improved
keep ground points instead of removing ground below 0.3m (ablation)EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06)t_rel (%): 1.450 -> 0.795Improved
stride-based sampling instead of FPS (ablation)EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06)t_rel (%): 5.734 -> 0.795Improved
stride-based sampling instead of random sampling (ablation)EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06)t_rel (%): 3.855 -> 0.795Improved
add projection-aware grouping (ablation)EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06)t_rel (%): 0.966 -> 0.795Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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