Papers
Topics
Authors
Recent
Search
2000 character limit reached

Quasi-Medial Distance Field (Q-MDF): A Robust Method for Approximating and Discretizing Neural Medial Axis

Published 23 Oct 2024 in cs.CV and cs.GR | (2410.17774v1)

Abstract: The medial axis, a lower-dimensional shape descriptor, plays an important role in the field of digital geometry processing. Despite its importance, robust computation of the medial axis transform from diverse inputs, especially point clouds with defects, remains a significant challenge. In this paper, we tackle the challenge by proposing a new implicit method that diverges from mainstream explicit medial axis computation techniques. Our key technical insight is the difference between the signed distance field (SDF) and the medial field (MF) of a solid shape is the unsigned distance field (UDF) of the shape's medial axis. This allows for formulating medial axis computation as an implicit reconstruction problem. Utilizing a modified double covering method, we extract the medial axis as the zero level-set of the UDF. Extensive experiments show that our method has enhanced accuracy and robustness in learning compact medial axis transform from thorny meshes and point clouds compared to existing methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. The power crust, unions of balls, and the medial axis transform. Computational Geometry 19, 2-3 (2001), 127–153.
  2. Dominique Attali and Annick Montanvert. 1996. Modeling noise for a better simplification of skeletons. In Proceedings of 3rd IEEE International Conference on Image Processing, Vol. 3. IEEE, 13–16.
  3. A benchmark for surface reconstruction. ACM Transactions on Graphics (TOG) 32, 2 (2013), 1–17.
  4. Skeletal structures. Shape Analysis and structuring (2008), 145–183.
  5. Harry Blum. 1967. A Transformation for Extracting New Descriptors of Shape. In Models for the Perception of Speech and Visual Form, Weiant Wathen-Dunn (Ed.). MIT Press, Cambridge, 362–380.
  6. Jonathan W Brandt. 1994. Convergence and continuity criteria for discrete approximations of the continuous planar skeleton. CVGIP: Image Understanding 59, 1 (1994), 116–124.
  7. Frédéric Chazal and André Lieutier. 2005. The “λ𝜆\lambdaitalic_λ-medial axis”. Graphical models 67, 4 (2005), 304–331.
  8. Frédéric Chazal and André Lieutier. 2008. Smooth manifold reconstruction from noisy and non-uniform approximation with guarantees. Computational Geometry 40, 2 (2008), 156–170.
  9. Zhiqin Chen and Hao Zhang. 2019. Learning implicit fields for generative shape modeling. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 5939–5948.
  10. Mattéo Clémot and Julie Digne. 2023. Neural skeleton: Implicit neural representation away from the surface. Computers & Graphics 114 (2023), 368–378.
  11. Accurate computation of the medial axis of a polyhedron. In Proceedings of the fifth ACM symposium on Solid modeling and applications. 179–190.
  12. Exact computation of the medial axis of a polyhedron. Computer Aided Geometric Design 21, 1 (2004), 65–98.
  13. Tamal K Dey and Wulue Zhao. 2004. Approximating the medial axis from the Voronoi diagram with a convergence guarantee. Algorithmica 38 (2004), 179–200.
  14. Coverage axis: Inner point selection for 3d shape skeletonization. In Computer Graphics Forum, Vol. 41. Wiley Online Library, 419–432.
  15. Tore: Token reduction for efficient human mesh recovery with transformer. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 15143–15155.
  16. Michael Garland and Paul S Heckbert. 1997. Surface simplification using quadric error metrics. In Proceedings of the 24th annual conference on Computer graphics and interactive techniques. 209–216.
  17. Point2MM: Learning medial mesh from point clouds. Computers & Graphics 115 (2023), 511–521.
  18. Medial axis approximation and unstable flow complex. In Proceedings of the twenty-second annual symposium on Computational geometry. 327–336.
  19. Wim H Hesselink and Jos BTM Roerdink. 2008. Euclidean skeletons of digital image and volume data in linear time by the integer medial axis transform. IEEE Transactions on Pattern Analysis and Machine Intelligence 30, 12 (2008), 2204–2217.
  20. Robust zero level-set extraction from unsigned distance fields based on double covering. ACM Transactions on Graphics (TOG) 42, 6 (2023), 1–15.
  21. Variational implicit point set surfaces. ACM Transactions on Graphics (TOG) 38, 4 (2019), 1–13.
  22. Surface reconstruction from point clouds: A survey and a benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024).
  23. Surface and curve skeletonization of large 3D models on the GPU. IEEE transactions on pattern analysis and machine intelligence 35, 6 (2012), 1495–1508.
  24. Michael Kazhdan and Hugues Hoppe. 2013. Screened poisson surface reconstruction. ACM Trans. Graph. 32, 3, Article 29 (July 2013), 13 pages. https://doi.org/10.1145/2487228.2487237
  25. Abc: A big cad model dataset for geometric deep learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 9601–9611.
  26. Medial elastics: Efficient and collision-ready deformation via medial axis transform. ACM Transactions on Graphics (TOG) 39, 3 (2020), 1–17.
  27. Medial IPC: accelerated incremental potential contact with medial elastics. ACM Transactions on Graphics 40, 4 (2021).
  28. Q-mat: Computing medial axis transform by quadratic error minimization. ACM Transactions on Graphics (TOG) 35, 1 (2015), 1–16.
  29. Point2skeleton: Learning skeletal representations from point clouds. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 4277–4286.
  30. Seg-mat: 3d shape segmentation using medial axis transform. IEEE transactions on visualization and computer graphics 28, 6 (2020), 2430–2444.
  31. William E Lorensen and Harvey E Cline. 1998. Marching cubes: A high resolution 3D surface construction algorithm. In Seminal graphics: pioneering efforts that shaped the field. 347–353.
  32. 3D medial axis point approximation using nearest neighbors and the normal field. The Visual Computer 28 (2012), 7–19.
  33. Discrete scale axis representations for 3D geometry. In ACM SIGGRAPH 2010 papers. 1–10.
  34. Victor Milenkovic. 1993. Robust Construction of the Voronoi Diagram of a Polyhedron.. In CCCG, Vol. 93. Citeseer, 473–478.
  35. Surface-Filling Curve Flows via Implicit Medial Axes. ACM Transactions on Graphics (TOG) 43, 4 (2024), 1–12.
  36. Kálmán Palágyi and Attila Kuba. 1999. A parallel 3D 12-subiteration thinning algorithm. Graphical Models and Image Processing 61, 4 (1999), 199–221.
  37. Q-MAT+: An error-controllable and feature-sensitive simplification algorithm for medial axis transform. Computer Aided Geometric Design 71 (2019), 16–29.
  38. Deepsdf: Learning continuous signed distance functions for shape representation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 165–174.
  39. GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesis. In ACM SIGGRAPH 2024 Conference Papers. 1–11.
  40. Chris Pudney. 1998. Distance-ordered homotopic thinning: a skeletonization algorithm for 3D digital images. Computer vision and image understanding 72, 3 (1998), 404–413.
  41. M Ramanathan and B Gurumoorthy. 2010. Interior medial axis transform computation of 3D objects bound by free-form surfaces. Computer-Aided Design 42, 12 (2010), 1217–1231.
  42. Deep medial fields. arXiv preprint arXiv:2106.03804 (2021).
  43. Martin Rumpf and Alexandru Telea. 2002. A continuous skeletonization method based on level sets. In EPRINTS-BOOK-TITLE. University of Groningen, Johann Bernoulli Institute for Mathematics and ….
  44. A survey on skeletonization algorithms and their applications. Pattern recognition letters 76 (2016), 3–12.
  45. An algorithm for the medial axis transform of 3D polyhedral solids. IEEE transactions on visualization and computer graphics 2, 1 (1996), 44–61.
  46. 3d skeletons: A state-of-the-art report. In Computer Graphics Forum, Vol. 35. Wiley Online Library, 573–597.
  47. A skeleton-bridged deep learning approach for generating meshes of complex topologies from single rgb images. In Proceedings of the ieee/cvf conference on computer vision and pattern recognition. 4541–4550.
  48. MATTopo: Topology-preserving Medial Axis Transform with Restricted Power Diagram. arXiv preprint arXiv:2403.18761 (2024).
  49. Computing medial axis transform with feature preservation via restricted power diagram. ACM Transactions on Graphics (TOG) 41, 6 (2022), 1–18.
  50. Coverage Axis++: Efficient Inner Point Selection for 3D Shape Skeletonization. In Computer Graphics Forum. Wiley Online Library, e15143.
  51. Deep Points Consolidation. ACM Transactions on Graphics (Proc. of SIGGRAPH Asia) 34, 6 (2015), 176:1–176:13.
  52. Voxel cores: Efficient, robust, and provably good approximation of 3d medial axes. ACM Transactions on Graphics (TOG) 37, 4 (2018), 1–13.
  53. DMAT: Deformable medial axis transform for animated mesh approximation. In Computer Graphics Forum, Vol. 37. Wiley Online Library, 301–311.
  54. P2MAT-NET: Learning medial axis transform from sparse point clouds. Computer Aided Geometric Design 80 (2020), 101874.
  55. Learning dynamics via graph neural networks for human pose estimation and tracking. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 8074–8084.
  56. Qingnan Zhou and Alec Jacobson. 2016. Thingi10k: A dataset of 10,000 3d-printing models. arXiv preprint arXiv:1605.04797 (2016).
  57. Generalized cylinder decomposition. ACM Trans. Graph. 34, 6 (2015), 171–1.

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

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

Continue Learning

We haven't generated follow-up questions for this paper yet.

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

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up