Research map / 3D vision / Face and shape
NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping
Junyuan Deng, Qi Wu, Xieyuanli Chen, Songpengcheng Xia, Zhen Sun, Guoqing Liu, Wenxian Yu, Ling Pei
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 ground separation to the SDF (ablation) | NeRF-LOAM · MaiCity (own odometry) | F-score: 48.78 -> 77.26 | Improved |
| add ground separation to the SDF (ablation) | NeRF-LOAM · Newer College (own odometry) | odometry success: failed without it; RMSE 0.15 with it | Improved |
| add ground separation to the SDF (ablation) | NeRF-LOAM · MaiCity | ATE RMSE: 0.20 -> 0.17 | Improved |
| add key-scan refinement (ablation) | NeRF-LOAM · Newer College (own odometry) | F-score: 61.10 -> 74.37 | Improved |
| add key-scan refinement (ablation) | NeRF-LOAM · MaiCity (own odometry) | F-score: 76.15 -> 77.26 | Improved |
| add key-scan refinement with ground-truth poses (ablation) | NeRF-LOAM · MaiCity (GT pose) | F-score: 92.80 -> 92.96 | No clear effect |
| add ground separation with ground-truth poses (ablation) | NeRF-LOAM · Newer College (GT pose) | Accuracy: Acc. 6.73 -> 6.86 with ground separation; Chamfer-L1 10.79 -> 11.24 | Mixed |
| use NeRF-LOAM mapping instead of SHINE or Vdbfusion with GT poses | mapping module · MaiCity (GT pose) | F-score: 90.16 -> 92.96 | Improved |
| increase voxel size beyond 20 cm (ablation) | NeRF-LOAM · Newer College | mapping quality | Hurt |
| use learned pre-trained odometry (DeLORA, PWC-LONet) on a new dataset | baselines · Newer College odometry | ATE RMSE: PWC-LONet 15.78 vs ours 0.15 | Hurt |
Closest papers by meaning
- NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields (AAAI 2024 · similarity 0.89)
- STGC-NeRF: Spatial-Temporal Geometric Consistency for LiDAR Neural Radiance Fields in Dynamic Scenes (AAAI 2025 · similarity 0.87)
- 3D LiDAR Mapping in Dynamic Environments using a 4D Implicit Neural Representation (CVPR 2024 · similarity 0.87)
- DeepPointMap: Advancing LiDAR SLAM with Unified Neural Descriptors (AAAI 2024 · similarity 0.87)
- DiffLO: Semantic-Aware LiDAR Odometry with Diffusion-Based Refinement (CVPR 2025 · similarity 0.86)
- LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesis (CVPR 2024 · 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.
