mlsanityData to 14 Oct 2026

Asymmetrical Siamese Network for Point Clouds Normal Estimation

arXiv 2406.09681 ↗First posted 14 Jun 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In recent years, deep learning-based point cloud normal estimation has made great progress. However, existing methods mainly rely on the PCPNet dataset, leading to overfitting. In addition, the correlation between point clouds with different noise scales remains unexplored, resulting in poor performance in cross-domain scenarios. In this paper, we explore the consistency of intrinsic features learned from clean and noisy point clouds using an Asymmetric Siamese Network architecture. By applying reasonable constraints between features extracted from different branches, we enhance the quality of normal estimation. Moreover, we introduce a novel multi-view normal estimation dataset that includes a larger variety of shapes with different noise levels. Evaluation of existing methods on this new dataset reveals their inability to adapt to different types of shapes, indicating a degree of overfitting. Extensive experiments show that the proposed dataset poses significant challenges for point cloud normal estimation and that our feature constraint mechanism effectively improves upon existing methods and reduces overfitting in current architectures.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 50 references that are in the map. First posted on arXiv 14 Jun 2024.

Builds on

21 of 50 references.

References · 21

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  4. 2020Point Transformercited by 1,470
  5. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 341
  6. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  7. 2020Points2Surf: Learning Implicit Surfaces from Point Cloud Patchescited by 122
  8. 2023Neural Kernel Surface Reconstructioncited by 104
  9. 2017PCPNET: Learning Local Shape Properties from Raw Point Cloudscited by 98
  10. 2020Pointfilter: Point Cloud Filtering via Encoder-Decoder Modelingcited by 50
  11. 2018Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds using Convolutional Neural Networkscited by 44
  12. 2020DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squarescited by 43
9 more
  1. 2022NeAF: Learning Neural Angle Fields for Point Normal Estimationcited by 38
  2. 2020Deep Feature-preserving Normal Estimation for Point Cloud Filteringcited by 36
  3. 2021AdaFit: Rethinking Learning-based Normal Estimation on Point Cloudscited by 29
  4. 2022Refine-Net: Normal Refinement Neural Network for Noisy Point Cloudscited by 23
  5. 2022HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfacescited by 22
  6. 2019Normal Estimation for 3D Point Clouds via Local Plane Constraint and Multi-scale Selectioncited by 20
  7. 2022GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimationcited by 20
  8. 2021Improvement of Normal Estimation for PointClouds via Simplifying Surface Fittingcited by 12
  9. 2021Fast and Accurate Normal Estimation for Point Cloud via Patch Stitchingcited by 8

Built on by

Not cited yet.