Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Diffusing Winding Gradients (DWG): A Parallel and Scalable Method for 3D Reconstruction from Unoriented Point Clouds (2405.13839v2)

Published 22 May 2024 in cs.GR

Abstract: This paper presents a new method, Diffusing Winding Gradients (DWG), for reconstructing watertight 3D surfaces from unoriented point clouds. Our method exploits the alignment between the gradients of the generalized winding number (GWN) field and globally consistent normals to orient points effectively. Starting with an unoriented point cloud, DWG initially assigns a random normal to each point. It computes the corresponding GWN field and extract a level set whose iso-value is the average GWN values across all input points. The gradients of this level set are then utilized to update the point normals. This cycle of recomputing the GWN field and updating point normals is repeated until the GWN level sets stabilize and their gradients cease to change. Unlike conventional methods, our method does not rely on solving linear systems or optimizing objective functions, which simplifies its implementation and enhances its suitability for efficient parallel execution. Experimental results demonstrate that our method significantly outperforms existing methods in terms of runtime performance. For large-scale models with 10 to 20 million points, our CUDA implementation on an NVIDIA GTX 4090 GPU achieves speeds 30-120 times faster than iPSR, the leading sequential method, tested on a high-end PC with an Intel i9 CPU. Additionally, by employing a screened variant of GWN, DWG demonstrates enhanced robustness against noise and outliers, and proves effective for models with thin structures and real-world inputs with overlapping and misaligned scans. For source code and more details, visit our project webpage: https://dwgtech.github.io/.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (48)
  1. Voronoi-based variational reconstruction of unoriented point sets. In Proceedings of the Fifth Eurographics Symposium on Geometry Processing (SGP ’07). Goslar, DEU, 39–48.
  2. The Power Crust. In Proceedings of the Sixth ACM Symposium on Solid Modeling and Applications. 249–266.
  3. Matan Atzmon and Yaron Lipman. 2020. SAL: Sign Agnostic Learning of Shapes From Raw Data. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, Los Alamitos, CA, USA, 2562–2571.
  4. Matan Atzmon and Yaron Lipman. 2021. SALD: Sign Agnostic Learning with Derivatives. In International Conference on Learning Representations (ICLR).
  5. Fast winding numbers for soups and clouds. ACM Trans. Graph. 37, 4 (2018).
  6. DiGS: Divergence guided shape implicit neural representation for unoriented point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 19323–19332.
  7. Alexandre Boulch and Renaud Marlet. 2022. POCO: Point Convolution for Surface Reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  8. Fatih Calakli and Gabriel Taubin. 2011. SSD: Smooth Signed Distance Surface Reconstruction. Computer Graphics Forum 30, 7 (2011), 1993–2002.
  9. Reconstruction and representation of 3D objects with radial basis functions. In Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH ’01). New York, NY, USA, 67–76.
  10. Deep Local Shapes: Learning local sdf priors for detailed 3d reconstruction. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIX 16. Springer, 608–625.
  11. Tamal K. Dey and Samrat Goswami. 2003. Tight Cocone: A Water-Tight Surface Reconstructor. In Proceedings of the Eighth ACM Symposium on Solid Modeling and Applications. 127–134.
  12. Tamal K Dey and Jian Sun. 2005. An Adaptive MLS Surface for Reconstruction with Guarantees.. In Symposium on Geometry processing. 43–52.
  13. Points2surf: learning implicit surfaces from point clouds. In Proceedings of the European Conference on Computer Vision (ECCV).
  14. Winding Numbers on Discrete Surfaces. ACM Trans. Graph. (2023).
  15. Eric Haines. 1994. Point in polygon strategies. Academic Press Professional, Inc., USA, 24–46.
  16. Surface reconstruction from unorganized points. In Proceedings of the 19th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH ’92). New York, NY, USA, 71–78.
  17. Iterative poisson surface reconstruction (iPSR) for unoriented points. ACM Trans. Graph. 41, 4 (2022).
  18. Consolidation of Unorganized Point Clouds for Surface Reconstruction. ACM Trans. Graph. 28, 5 (dec 2009), 7 pages.
  19. Edge-Aware Point Set Resampling. ACM Trans. Graph. 32, 1, Article 9 (feb 2013), 12 pages.
  20. A Neural Galerkin Solver for Accurate Surface Reconstruction. ACM Trans. Graph. 41, 6 (2022).
  21. Variational implicit point set surfaces. ACM Trans. Graph. 38, 4 (2019), 124:1–124:13.
  22. Robust inside-outside segmentation using generalized winding numbers. ACM Trans. Graph. 32, 4 (2013).
  23. Local implicit grid representations for 3d scenes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  24. Michael Kazhdan. 2005. Reconstruction of solid models from oriented point sets. In Proceedings of the third Eurographics symposium on Geometry processing. 73–es.
  25. Poisson Surface Reconstruction with Envelope Constraints. Computer Graphics Forum 30, 7 (2020), 1993–2002.
  26. Michael Kazhdan and Hugues Hoppe. 2013. Screened poisson surface reconstruction. ACM Trans. Graph. 32, 3 (2013).
  27. Poisson surface reconstruction. In Eurographics Symposium on Geometry Processing.
  28. Ravikrishna Kolluri. 2008. Provably good moving least squares. ACM Transactions on Algorithms (TALG) (2008).
  29. Patch-Grid: An Efficient and Feature-Preserving Neural Implicit Surface Representation. arXiv:2308.13934 [cs.GR]
  30. Surface Reconstruction from Point Clouds without Normals by Parametrizing the Gauss Formula. ACM Trans. Graph. 42, 2 (2022).
  31. Consistent Point Orientation for Manifold Surfaces via Boundary Integration. In Proceedings of ACM SIGGRAPH ’24.
  32. William E. Lorensen and Harvey E. Cline. 1987. Marching Cubes: A High Resolution 3D Surface Construction Algorithm. In Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH ’87). 163–169.
  33. Surface Reconstruction from Point Clouds by Learning Predictive Context Priors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  34. Occupancy Networks: Learning 3D Reconstruction in Function Space. In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR).
  35. Orienting point clouds with dipole propagation. ACM Trans. Graph. 40, 4 (2021).
  36. Multi-level partition of unity implicits. ACM Trans. Graph. 22, 3 (2003), 463–470.
  37. Feature preserving point set surfaces based on non-linear kernel regression. In Computer Graphics Forum.
  38. DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 165–174.
  39. Shape As Points: A Differentiable Poisson Solver. In Advances in Neural Information Processing Systems (NeurIPS).
  40. A Variational Taxonomy for Surface Reconstruction from Oriented Points. Computer Graphics Forum 33, 5 (2014), 195–204.
  41. Interpolating and Approximating Implicit Surfaces from Polygon Soup. In ACM SIGGRAPH 2004 Papers.
  42. Convolutional Occupancy Networks. In Proceedings of the European Conference on Computer Vision (ECCV).
  43. SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision.
  44. OctField: Hierarchical Implicit Functions for 3D Modeling. In Advances in Neural Information Processing Systems (NeurIPS).
  45. Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations. ACM Trans. Graph. 41, 4 (2022), 15 pages.
  46. Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessian. ACM Trans. Graph. 42, 6 (2023).
  47. Globally Consistent Normal Orientation for Point Clouds by Regularizing the Winding-Number Field. ACM Trans. Graph. 42, 4 (2023).
  48. Learning Consistency-Aware Unsigned Distance Functions Progressively from Raw Point Clouds. In Advances in Neural Information Processing Systems (NeurIPS).

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now