mlsanityData to 7 Oct 2026

Consistent Point Orientation for Manifold Surfaces via Boundary Integration

arXiv 2407.03165 ↗First posted 3 Jul 2024cs.CV cs.GRcited by 4

Not on the map. Why?

Abstract (arXiv)

This paper introduces a new approach for generating globally consistent normals for point clouds sampled from manifold surfaces. Given that the generalized winding number (GWN) field generated by a point cloud with globally consistent normals is a solution to a PDE with jump boundary conditions and possesses harmonic properties, and the Dirichlet energy of the GWN field can be defined as an integral over the boundary surface, we formulate a boundary energy derived from the Dirichlet energy of the GWN. Taking as input a point cloud with randomly oriented normals, we optimize this energy to restore the global harmonicity of the GWN field, thereby recovering the globally consistent normals. Experiments show that our method outperforms state-of-the-art approaches, exhibiting enhanced robustness to noise, outliers, complex topologies, and thin structures. Our code can be found at urlhttps://github.com/liuweizhou319/BIM.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 15 of its 50 references that are in the map. First posted on arXiv 3 Jul 2024.

Builds on

15 of 50 references.

References · 15

  1. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  2. 2017PCPNET: Learning Local Shape Properties from Raw Point Cloudscited by 97
  3. 2020Pointfilter: Point Cloud Filtering via Encoder-Decoder Modelingcited by 50
  4. 2021Neural Points: Point Cloud Representation with Neural Fields for Arbitrary Upsamplingcited by 48
  5. 2022NeAF: Learning Neural Angle Fields for Point Normal Estimationcited by 38
  6. 2023Globally Consistent Normal Orientation for Point Clouds by Regularizing the Winding-Number Fieldcited by 37
  7. 2021Orienting Point Clouds with Dipole Propagationcited by 31
  8. 2022Iterative Poisson Surface Reconstruction (iPSR) for Unoriented Pointscited by 31
  9. 2021AdaFit: Rethinking Learning-based Normal Estimation on Point Cloudscited by 29
  10. 2022Stochastic Poisson Surface Reconstructioncited by 13
  11. 2023Neural Gradient Learning and Optimization for Oriented Point Normal Estimationcited by 11
  12. 2023NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Functioncited by 10
3 more
  1. 2022RFEPS: Reconstructing Feature-line Equipped Polygonal Surfacecited by 7
  2. 2023Neural Stochastic Screened Poisson Reconstructioncited by 7
  3. 2014Consistently Orienting Facets in Polygon Meshes by Minimizing the Dirichlet Energy of Generalized Winding Numberscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2025A Divide-and-Conquer Approach for Global Orientation of Non-Watertight Scene-Level Point Clouds Using 0-1 Integer Optimizationcited by 1
  2. 2024OCMG-Net: Neural Oriented Normal Refinement for Unstructured Point Cloudscited by 0
  3. 2025Voronoi-Assisted Optimization for Diffusing Unsigned Distance Fields from Unoriented Pointscited by 0
  4. 2026Joint Orientation and Weight Optimization for Robust Watertight Surface Reconstruction via Dirichlet-Regularized Winding Fieldscited by 0