Research map / Point clouds / Registration and matching
Efficient 3D Deep LiDAR Odometry
Guangming Wang, Xinrui Wu, Shuyang Jiang, Zhe Liu, Hesheng Wang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add the embedding mask (ablation) | EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06) | t_rel (%): 1.218 -> 0.795 | Improved |
| add hierarchical mask optimization (ablation) | EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06) | t_rel (%): 0.898 -> 0.795 | Improved |
| add pose warp-refinement module (ablation) | EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06) | t_rel (%): 3.76 -> 0.795 | Improved |
| add pose warping to hierarchical refinement (ablation) | EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06) | t_rel (%): 3.145 -> 0.795 | Improved |
| add the cost volume (ablation) | EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06) | t_rel (%): 11.790 -> 0.795 | Improved |
| 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 -> 0.795 | Improved |
| 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 -> 0.795 | Improved |
| 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 -> 0.795 | Improved |
| 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 -> 0.795 | Improved |
| stride-based sampling instead of FPS (ablation) | EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06) | t_rel (%): 5.734 -> 0.795 | Improved |
| stride-based sampling instead of random sampling (ablation) | EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06) | t_rel (%): 3.855 -> 0.795 | Improved |
| add projection-aware grouping (ablation) | EfficientLO-Net · KITTI odometry seq 07-10 mean (train 00-06) | t_rel (%): 0.966 -> 0.795 | Improved |
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.
- PWCLO-Net — PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimization (CVPR 2021) · better on 2 of 2 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
- DeepPointMap: Advancing LiDAR SLAM with Unified Neural Descriptors (AAAI 2024 · similarity 0.87)
- LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes (CVPR 2024 · similarity 0.86)
- Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation (AAAI 2025 · similarity 0.86)
- An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains (CVPR 2024 · similarity 0.86)
- A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration (NeurIPS 2024 · similarity 0.86)
- DiffLO: Semantic-Aware LiDAR Odometry with Diffusion-Based Refinement (CVPR 2025 · similarity 0.86)
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.
