Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
10 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
3 tokens/sec
DeepSeek R1 via Azure Pro
51 tokens/sec
2000 character limit reached

View-Dependent Octree-based Mesh Extraction in Unbounded Scenes for Procedural Synthetic Data (2312.08364v1)

Published 13 Dec 2023 in cs.CV

Abstract: Procedural synthetic data generation has received increasing attention in computer vision. Procedural signed distance functions (SDFs) are a powerful tool for modeling large-scale detailed scenes, but existing mesh extraction methods have artifacts or performance profiles that limit their use for synthetic data. We propose OcMesher, a mesh extraction algorithm that efficiently handles high-detail unbounded scenes with perfect view-consistency, with easy export to downstream real-time engines. The main novelty of our solution is an algorithm to construct an octree based on a given SDF and multiple camera views. We performed extensive experiments, and show our solution produces better synthetic data for training and evaluation of computer vision models.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. Vectron volume for cinema 4d: https://www.machina-infinitum.com/vectron-volume.
  2. Deep equilibrium optical flow estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 620–630, 2022.
  3. A naturalistic open source movie for optical flow evaluation. In Computer Vision–ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part VI 12, pages 611–625. Springer, 2012.
  4. Blender Online Community. Blender - a 3D modelling and rendering package. Blender Foundation, Stichting Blender Foundation, Amsterdam, 2018.
  5. Gigavoxels: Ray-guided streaming for efficient and detailed voxel rendering. In Proceedings of the 2009 symposium on Interactive 3D graphics and games, pages 15–22, 2009.
  6. ProcTHOR: Large-scale embodied AI using procedural generation. arXiv preprint arXiv:2206.06994, 2022.
  7. Meta-sim2: Unsupervised learning of scene structure for synthetic data generation. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XVII 16, pages 715–733. Springer, 2020.
  8. An efficient method of triangulating equi-valued surfaces by using tetrahedral cells. IEICE Transactions on Information and Systems, 74:214–224, 1991.
  9. Texturing & modeling: a procedural approach. Morgan Kaufmann, 2003.
  10. Epic Games. Unreal engine.
  11. Gunnar Farnebäck. Two-frame motion estimation based on polynomial expansion. In Image Analysis: 13th Scandinavian Conference, SCIA 2003 Halmstad, Sweden, June 29–July 2, 2003 Proceedings 13, pages 363–370. Springer, 2003.
  12. Segment tracing using local lipschitz bounds. In Computer Graphics Forum, pages 545–554. Wiley Online Library, 2020.
  13. Ryan Geiss. Generating complex procedural terrains using the gpu. GPU gems, 3(7):37, 2007.
  14. Topology preserving and controlled topology simplifying multiresolution isosurface extraction. IEEE, 2000.
  15. Unpopping: Solving the image-space blend problem for smooth discrete lod transitions. In Computer Graphics Forum, pages 46–49. Wiley Online Library, 2007.
  16. A single-pass gpu ray casting framework for interactive out-of-core rendering of massive volumetric datasets. The Visual Computer, 24:797–806, 2008.
  17. Kubric: A scalable dataset generator. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3749–3761, 2022.
  18. Interactive view-dependent rendering of large isosurfaces. IEEE, 2002.
  19. John C Hart. Sphere tracing: A geometric method for the antialiased ray tracing of implicit surfaces. The Visual Computer, 12(10):527–545, 1996.
  20. Hugues Hoppe. View-dependent refinement of progressive meshes. In Proceedings of the 24th annual conference on Computer graphics and interactive techniques, pages 189–198, 1997.
  21. Configurable 3d scene synthesis and 2d image rendering with per-pixel ground truth using stochastic grammars. International Journal of Computer Vision, 126:920–941, 2018.
  22. Intersection-free contouring on an octree grid. In Proceedings of Pacific graphics. Citeseer, 2006.
  23. Dual contouring of hermite data. In Proceedings of the 29th annual conference on Computer graphics and interactive techniques, pages 339–346, 2002.
  24. Procsy: Procedural synthetic dataset generation towards influence factor studies of semantic segmentation networks. In CVPR workshops, page 4, 2019.
  25. Label-free synthetic pretraining of object detectors. arXiv preprint arXiv:2208.04268, 2022.
  26. Practical stereo matching via cascaded recurrent network with adaptive correlation. In CVPR, 2022.
  27. Interiornet: Mega-scale multi-sensor photo-realistic indoor scenes dataset. arXiv preprint arXiv:1809.00716, 2018.
  28. Real-time, continuous level of detail rendering of height fields. In Proceedings of the 23rd annual conference on Computer graphics and interactive techniques, pages 109–118, 1996.
  29. Coupled iterative refinement for 6d multi-object pose estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6728–6737, 2022.
  30. Progressive view-dependent isosurface propagation. In Data Visualization 2001: Proceedings of the Joint Eurographics—IEEE TCVG Symposium on Visualization in Ascona, Switzerland, May 28–30, 2001, pages 223–232. Springer, 2001.
  31. View dependent isosurface extraction. In Proceedings Visualization’98 (Cat. No. 98CB36276), pages 175–180. IEEE, 1998.
  32. Marching cubes: A high resolution 3d surface construction algorithm. In Seminal graphics: pioneering efforts that shaped the field, pages 347–353. 1998.
  33. Multiview stereo with cascaded epipolar raft. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXXI, pages 734–750. Springer, 2022.
  34. Donald Meagher. Octree encoding: A new technique for the representation, manipulation and display of arbitrary 3-d objects by computer, 1980.
  35. Forest Kenton Musgrave. Methods for realistic landscape imaging. Yale University, 1993.
  36. F Kenton Musgrave. Qaeb rendering for procedural models. Ebert et al. [9], pages 509–528.
  37. Efficient computation of the topology of level sets. In IEEE Visualization, 2002. VIS 2002., pages 187–194. IEEE, 2002.
  38. Ken Perlin. An image synthesizer. ACM Siggraph Computer Graphics, 19(3):287–296, 1985.
  39. Ken Perlin. Noise, hypertexture, antialiasing and gesture. Ebert et al. [9], pages 337–412.
  40. Kizamu: A system for sculpting digital characters. In Proceedings of the 28th annual conference on Computer graphics and interactive techniques, pages 47–56, 2001.
  41. Infinite photorealistic worlds using procedural generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12630–12641, 2023.
  42. Playing for data: Ground truth from computer games. In ECCV, pages 102–118. Springer, 2016.
  43. Real-time isosurface extraction with view-dependent level of detail and applications. In Computer Graphics Forum, pages 103–115. Wiley Online Library, 2015.
  44. Videoflow: Exploiting temporal cues for multi-frame optical flow estimation. arXiv preprint arXiv:2303.08340, 2023.
  45. Raft: Recurrent all-pairs field transforms for optical flow. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II 16, pages 402–419. Springer, 2020.
  46. Procedural modeling and physically based rendering for synthetic data generation in automotive applications. arXiv preprint arXiv:1710.06270, 2017.
  47. Tartanair: A dataset to push the limits of visual slam. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 4909–4916. IEEE, 2020.
  48. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4):600–612, 2004.
  49. Extraction of crack-free isosurfaces from adaptive mesh refinement data. Springer, 2003.
  50. Rephael Wenger. Isosurfaces: geometry, topology, and algorithms. CRC Press, 2013.
  51. Synscapes: A photorealistic synthetic dataset for street scene parsing. arXiv preprint arXiv:1810.08705, 2018.
  52. Blendedmvs: A large-scale dataset for generalized multi-view stereo networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1790–1799, 2020.
  53. Multiresolution tetrahedral framework for visualizing regular volume data. In Proceedings. Visualization’97 (Cat. No. 97CB36155), pages 135–142. IEEE, 1997.

Summary

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

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

Follow-up Questions

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

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

GitHub

  1. GitHub - princeton-vl/OcMesher (42 stars)