Research map / Point clouds / Shape and surface completion
ESNE: Efficient Surface Normal Estimation for LiDAR Point Clouds with Sequential Modeling and Variability Guidance
Kohei Matsuzaki, Keisuke Nonaka
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 |
|---|---|---|---|
| replace LiSu method with ESNE | LiSu baseline · LiSu | mean angular error (deg): 6.26 -> 4.17 | Improved |
| replace LiSu method with ESNE | LiSu baseline · LiSu | inference time (s): 0.08 -> 0.04 | Improved |
| add SLA and VFR on top of SSM (ablation) | ESNE · LiSu | mean angular error (deg): 5.38 -> 4.17 | Improved |
| add VFR (ablation) | ESNE · LiSu | mean angular error (deg): 4.29 -> 4.17 | Improved |
| add SSM (ablation) | ESNE · LiSu | mean angular error (deg): 4.33 -> 4.17 | Improved |
| use spatial k-NN instead of sequential k-NN (ablation) | ESNE · LiSu | mean angular error (deg): 4.17 -> 3.70 | Improved |
| use spatial k-NN instead of sequential k-NN (ablation) | ESNE · LiSu | inference time (ms): 41.5 -> 495.2 | Hurt |
| increase SLA neighbours k from 3 to 15 (ablation) | ESNE · LiSu | mean angular error (deg): 5.04 -> 4.03 | Improved |
| increase k from 9 to 15 (ablation) | ESNE · LiSu | inference time (ms): 41.5 -> 51.0 | Hurt |
| use Z-order instead of Hilbert serialization (ablation) | ESNE · LiSu | mean angular error (deg): 4.17 -> 4.23 | No clear effect |
| add noise sigma 0.01 to test set | ESNE · LiSu | mean angular error (deg): 4.17 -> 4.32 | Hurt |
| use ESNE normals for NKSR reconstruction instead of LiSu normals | NKSR · CARLA (Original) | CD-L1: 0.0362 -> 0.0357 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- CMG-Net — CMG-Net: Robust Normal Estimation for Point Clouds via Chamfer Normal Distance and Multi-Scale Geometry (AAAI 2024) · better on 2 of 2 shared results
- SHS-Net — SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds (CVPR 2023) · better on 2 of 2 shared results
- GraphFit — GraphFit: Learning Multi-Scale Graph-Convolutional Representation for Point Cloud Normal Estimation (ECCV 2022) · 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
- LiSu: A Dataset and Method for LiDAR Surface Normal Estimation (CVPR 2025 · similarity 0.90)
- High-quality Point Cloud Oriented Normal Estimation via Hybrid Angular and Euclidean Distance Encoding (CVPR 2025 · similarity 0.87)
- Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation (CVPR 2023 · similarity 0.87)
- LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes (CVPR 2024 · similarity 0.85)
- TULIP: Transformer for Upsampling of LiDAR Point Clouds (CVPR 2024 · similarity 0.85)
- PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2025 · similarity 0.85)
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.
