mlsanityData to 7 Oct 2026

AdaFit: Rethinking Learning-based Normal Estimation on Point Clouds

arXiv 2108.05836 ↗First posted 12 Aug 2021cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

This paper presents a neural network for robust normal estimation on point clouds, named AdaFit, that can deal with point clouds with noise and density variations. Existing works use a network to learn point-wise weights for weighted least squares surface fitting to estimate the normals, which has difficulty in finding accurate normals in complex regions or containing noisy points. By analyzing the step of weighted least squares surface fitting, we find that it is hard to determine the polynomial order of the fitting surface and the fitting surface is sensitive to outliers. To address these problems, we propose a simple yet effective solution that adds an additional offset prediction to improve the quality of normal estimation. Furthermore, in order to take advantage of points from different neighborhood sizes, a novel Cascaded Scale Aggregation layer is proposed to help the network predict more accurate point-wise offsets and weights. Extensive experiments demonstrate that AdaFit achieves state-of-the-art performance on both the synthetic PCPNet dataset and the real-word SceneNN dataset.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 13 of its 38 references that are in the map. First posted on arXiv 12 Aug 2021.

Builds on

13 of 38 references.

References · 13

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  5. 2019PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Cloudscited by 99
  6. 2017PCPNET: Learning Local Shape Properties from Raw Point Cloudscited by 97
  7. 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
  8. 2019Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaningcited by 58
  9. 2020Pointfilter: Point Cloud Filtering via Encoder-Decoder Modelingcited by 50
  10. 2018Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds using Convolutional Neural Networkscited by 44
  11. 2020DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squarescited by 43
  12. 2020Deep Feature-preserving Normal Estimation for Point Cloud Filteringcited by 36
1 more
  1. 2019Normal Estimation for 3D Point Clouds via Local Plane Constraint and Multi-scale Selectioncited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 9; 2024: 7; 2025: 5; 2026: 2.

29 papers.

Sort:

By area:

  1. 2022NeAF: Learning Neural Angle Fields for Point Normal Estimationcited by 38
  2. 2023IterativePFN: True Iterative Point Cloud Filteringcited by 28
  3. 2022HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfacescited by 22
  4. 2022GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimationcited by 20
  5. 2024Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mappingcited by 15
  6. 2023Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimationcited by 13
  7. 2022Contrastive Learning for Joint Normal Estimation and Point Cloud Filteringcited by 12
  8. 2022PCDNF: Revisiting Learning-based Point Cloud Denoising via Joint Normal Filteringcited by 11
  9. 2023Neural Gradient Learning and Optimization for Oriented Point Normal Estimationcited by 11
  10. 2023Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimationcited by 10
  11. 2023NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Functioncited by 10
  12. 2022Semi-signed prioritized neural fitting for surface reconstruction from unoriented point cloudscited by 8
17 more
  1. 2023MSECNet: Accurate and Robust Normal Estimation for 3D Point Clouds by Multi-Scale Edge Conditioningcited by 6
  2. 2023CMG-Net: Robust Normal Estimation for Point Clouds via Chamfer Normal Distance and Multi-scale Geometrycited by 6
  3. 2024Consistent Point Orientation for Manifold Surfaces via Boundary Integrationcited by 4
  4. 2025PFF-Net: Patch Feature Fitting for Point Cloud Normal Estimationcited by 3
  5. 2025Learning Normals of Noisy Points by Local Gradient-Aware Surface Filteringcited by 2
  6. 2023Weighted Point Cloud Normal Estimationcited by 1
  7. 2025LiSu: A Dataset and Method for LiDAR Surface Normal Estimationcited by 1
  8. 2025Self-Supervised Implicit Attention Priors for Point Cloud Reconstructioncited by 1
  9. 2026GLASS: Geometry-aware Local Alignment and Structure Synchronization Network for 2D-3D Registrationcited by 1
  10. 2023PointNorm-Net: Self-Supervised Normal Prediction of 3D Point Clouds via Multi-Modal Distribution Estimationcited by 0
  11. 2024Surface Normal Estimation with Transformerscited by 0
  12. 2024E3-Net: Efficient E(3)-Equivariant Normal Estimation Networkcited by 0
  13. 2024Asymmetrical Siamese Network for Point Clouds Normal Estimationcited by 0
  14. 2024Refining 3D Point Cloud Normal Estimation via Sample Selectioncited by 0
  15. 2024OCMG-Net: Neural Oriented Normal Refinement for Unstructured Point Cloudscited by 0
  16. 2025MambaH-Fit: Rethinking Hyper-surface Fitting-based Point Cloud Normal Estimation via State Space Modellingcited by 0
  17. 2026CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representationcited by 0