Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstruction (2405.15188v1)

Published 24 May 2024 in cs.CV

Abstract: Reverse engineering CAD models from raw geometry is a classic but challenging research problem. In particular, reconstructing the CAD modeling sequence from point clouds provides great interpretability and convenience for editing. To improve upon this problem, we introduce geometric guidance into the reconstruction network. Our proposed model, PS-CAD, reconstructs the CAD modeling sequence one step at a time. At each step, we provide two forms of geometric guidance. First, we provide the geometry of surfaces where the current reconstruction differs from the complete model as a point cloud. This helps the framework to focus on regions that still need work. Second, we use geometric analysis to extract a set of planar prompts, that correspond to candidate surfaces where a CAD extrusion step could be started. Our framework has three major components. Geometric guidance computation extracts the two types of geometric guidance. Single-step reconstruction computes a single candidate CAD modeling step for each provided prompt. Single-step selection selects among the candidate CAD modeling steps. The process continues until the reconstruction is completed. Our quantitative results show a significant improvement across all metrics. For example, on the dataset DeepCAD, PS-CAD improves upon the best published SOTA method by reducing the geometry errors (CD and HD) by 10%, and the structural error (ECD metric) by about 15%.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Suzanne F. Buchele and Richard H. Crawford. 2004. Three-dimensional halfspace constructive solid geometry tree construction from implicit boundary representations. Comput. Aided Des. 36, 11 (2004), 1063–1073. https://doi.org/10.1016/J.CAD.2004.01.006
  2. CvxNet: Learnable Convex Decomposition. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020. Computer Vision Foundation / IEEE, 31–41. https://doi.org/10.1109/CVPR42600.2020.00011
  3. InverseCSG: automatic conversion of 3D models to CSG trees. ACM Trans. Graph. 37, 6 (2018), 213. https://doi.org/10.1145/3272127.3275006
  4. Write, Execute, Assess: Program Synthesis with a REPL. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d’Alché-Buc, Emily B. Fox, and Roman Garnett (Eds.). 9165–9174. https://proceedings.neurips.cc/paper/2019/hash/50d2d2262762648589b1943078712aa6-Abstract.html
  5. Pierre-Alain Fayolle and Alexander A. Pasko. 2016. An evolutionary approach to the extraction of object construction trees from 3D point clouds. Comput. Aided Des. 74 (2016), 1–17. https://doi.org/10.1016/J.CAD.2016.01.001
  6. Meta-representation of shape families. ACM Trans. Graph. 33, 4 (2014), 34:1–34:11. https://doi.org/10.1145/2601097.2601185
  7. BPNet: Bézier Primitive Segmentation on 3D Point Clouds. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI 2023, 19th-25th August 2023, Macao, SAR, China. ijcai.org, 754–762. https://doi.org/10.24963/IJCAI.2023/84
  8. ComplexGen: CAD reconstruction by B-rep chain complex generation. ACM Trans. Graph. 41, 4 (2022), 129:1–129:18. https://doi.org/10.1145/3528223.3530078
  9. Implicit Conversion of Manifold B-Rep Solids by Neural Halfspace Representation. ACM Trans. Graph. 41, 6 (2022), 276:1–276:15. https://doi.org/10.1145/3550454.3555502
  10. Karim Hamza and Kazuhiro Saitou. 2004. Optimization of Constructive Solid Geometry Via a Tree-Based Multi-objective Genetic Algorithm. In Genetic and Evolutionary Computation - GECCO 2004, Genetic and Evolutionary Computation Conference, Seattle, WA, USA, June 26-30, 2004, Proceedings, Part II (Lecture Notes in Computer Science, Vol. 3103), Kalyanmoy Deb, Riccardo Poli, Wolfgang Banzhaf, Hans-Georg Beyer, Edmund K. Burke, Paul J. Darwen, Dipankar Dasgupta, Dario Floreano, James A. Foster, Mark Harman, Owen Holland, Pier Luca Lanzi, Lee Spector, Andrea Tettamanzi, Dirk Thierens, and Andrew M. Tyrrell (Eds.). Springer, 981–992. https://doi.org/10.1007/978-3-540-24855-2_110
  11. Masked Autoencoders Are Scalable Vision Learners. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 15979–15988. https://doi.org/10.1109/CVPR52688.2022.01553
  12. PLAD: Learning to Infer Shape Programs with Pseudo-Labels and Approximate Distributions. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 9861–9870. https://doi.org/10.1109/CVPR52688.2022.00964
  13. UCSG-NET- Unsupervised Discovering of Constructive Solid Geometry Tree. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc’Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https://proceedings.neurips.cc/paper/2020/hash/63d5fb54a858dd033fe90e6e4a74b0f0-Abstract.html
  14. CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention. arXiv:2402.17678 [cs.CV]
  15. Learning part-based templates from large collections of 3D shapes. ACM Trans. Graph. 32, 4 (2013), 70:1–70:12. https://doi.org/10.1145/2461912.2461933
  16. Segment Anything. In IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023. IEEE, 3992–4003. https://doi.org/10.1109/ICCV51070.2023.00371
  17. John F Kolen and Stefan C Kremer. 2001. A field guide to dynamical recurrent networks. John Wiley & Sons.
  18. Constructive solid geometry for polyhedral objects. In Proceedings of the 13th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1986, Dallas, Texas, USA, August 18-22, 1986, David C. Evans and Russell J. Athay (Eds.). ACM, 161–170. https://doi.org/10.1145/15922.15904
  19. Reconstructing editable prismatic CAD from rounded voxel models. In SIGGRAPH Asia 2022 Conference Papers, SA 2022, Daegu, Republic of Korea, December 6-9, 2022, Soon Ki Jung, Jehee Lee, and Adam W. Bargteil (Eds.). ACM, 53:1–53:9. https://doi.org/10.1145/3550469.3555424
  20. Supervised Fitting of Geometric Primitives to 3D Point Clouds. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019. Computer Vision Foundation / IEEE, 2652–2660. https://doi.org/10.1109/CVPR.2019.00276
  21. SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operations. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023. IEEE, 16816–16826. https://doi.org/10.1109/CVPR52729.2023.01613
  22. Surface and Edge Detection for Primitive Fitting of Point Clouds. In ACM SIGGRAPH 2023 Conference Proceedings, SIGGRAPH 2023, Los Angeles, CA, USA, August 6-10, 2023, Erik Brunvand, Alla Sheffer, and Michael Wimmer (Eds.). ACM, 44:1–44:10. https://doi.org/10.1145/3588432.3591522
  23. MultiCAD: Contrastive Representation Learning for Multi-modal 3D Computer-Aided Design Models. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 1766–1776.
  24. Masked Autoencoders for Point Cloud Self-supervised Learning. In Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part II (Lecture Notes in Computer Science, Vol. 13662), Shai Avidan, Gabriel J. Brostow, Moustapha Cissé, Giovanni Maria Farinella, and Tal Hassner (Eds.). Springer, 604–621. https://doi.org/10.1007/978-3-031-20086-1_35
  25. DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019. Computer Vision Foundation / IEEE, 165–174. https://doi.org/10.1109/CVPR.2019.00025
  26. Superquadrics Revisited: Learning 3D Shape Parsing Beyond Cuboids. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019. Computer Vision Foundation / IEEE, 10344–10353. https://doi.org/10.1109/CVPR.2019.01059
  27. CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing. In 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021. IEEE, 12458–12467. https://doi.org/10.1109/ICCV48922.2021.01225
  28. ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing. In Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part II (Lecture Notes in Computer Science, Vol. 13662), Shai Avidan, Gabriel J. Brostow, Moustapha Cissé, Giovanni Maria Farinella, and Tal Hassner (Eds.). Springer, 482–498. https://doi.org/10.1007/978-3-031-20086-1_28
  29. Efficient RANSAC for Point-Cloud Shape Detection. Comput. Graph. Forum 26, 2 (2007), 214–226. https://doi.org/10.1111/J.1467-8659.2007.01016.X
  30. Vadim Shapiro and Donald L. Vossler. 1991. Construction and optimization of CSG representations. Comput. Aided Des. 23, 1 (1991), 4–20. https://doi.org/10.1016/0010-4485(91)90077-A
  31. Vadim Shapiro and Donald L. Vossler. 1993. Separation for Boundary to CSG Conversion. ACM Trans. Graph. 12, 1 (1993), 35–55. https://doi.org/10.1145/169728.169723
  32. CSGNet: Neural Shape Parser for Constructive Solid Geometry. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018. Computer Vision Foundation / IEEE Computer Society, 5515–5523. https://doi.org/10.1109/CVPR.2018.00578
  33. Neural Shape Parsers for Constructive Solid Geometry. IEEE Trans. Pattern Anal. Mach. Intell. 44, 5 (2022), 2628–2640. https://doi.org/10.1109/TPAMI.2020.3044749
  34. ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds. In Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part VII (Lecture Notes in Computer Science, Vol. 12352), Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (Eds.). Springer, 261–276. https://doi.org/10.1007/978-3-030-58571-6_16
  35. David Stutz. 2017. Learning Shape Completion from Bounding Boxes with CAD Shape Priors. http://davidstutz.de/.
  36. David Stutz and Andreas Geiger. 2018. Learning 3D Shape Completion from Laser Scan Data with Weak Supervision. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society.
  37. Learning shape abstractions by assembling volumetric primitives. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2635–2643.
  38. Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 11840–11850. https://doi.org/10.1109/CVPR52688.2022.01155
  39. Roreg: Pairwise point cloud registration with oriented descriptors and local rotations. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023).
  40. PIE-NET: Parametric Inference of Point Cloud Edges. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc’Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https://proceedings.neurips.cc/paper/2020/hash/e94550c93cd70fe748e6982b3439ad3b-Abstract.html
  41. Fusion 360 gallery: a dataset and environment for programmatic CAD construction from human design sequences. ACM Trans. Graph. 40, 4 (2021), 54:1–54:24. https://doi.org/10.1145/3450626.3459818
  42. Constructing 3D CSG Models from 3D Raw Point Clouds. Comput. Graph. Forum 37, 5 (2018), 221–232. https://doi.org/10.1111/CGF.13504
  43. DeepCAD: A Deep Generative Network for Computer-Aided Design Models. In 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021. IEEE, 6752–6762. https://doi.org/10.1109/ICCV48922.2021.00670
  44. Hierarchical Neural Coding for Controllable CAD Model Generation. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA (Proceedings of Machine Learning Research, Vol. 202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 38443–38461. https://proceedings.mlr.press/v202/xu23f.html
  45. Inferring CAD Modeling Sequences Using Zone Graphs. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19-25, 2021. Computer Vision Foundation / IEEE, 6062–6070. https://doi.org/10.1109/CVPR46437.2021.00600
  46. SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks. In International Conference on Machine Learning. PMLR, 24698–24724.
  47. HPNet: Deep Primitive Segmentation Using Hybrid Representations. In 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021. IEEE, 2733–2742. https://doi.org/10.1109/ICCV48922.2021.00275
  48. D22{}^{\mbox{2}}start_FLOATSUPERSCRIPT 2 end_FLOATSUPERSCRIPTCSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). http://papers.nips.cc/paper_files/paper/2023/hash/4732d425125832887f6c5a9675d49ead-Abstract-Conference.html
  49. CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 11758–11768. https://doi.org/10.1109/CVPR52688.2022.01147
  50. NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point Cloud. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023. IEEE, 13601–13610. https://doi.org/10.1109/CVPR52729.2023.01307

Summary

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

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

Tweets