Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 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

P2CADNet: An End-to-End Reconstruction Network for Parametric 3D CAD Model from Point Clouds (2310.02638v1)

Published 4 Oct 2023 in cs.CV

Abstract: Computer Aided Design (CAD), especially the feature-based parametric CAD, plays an important role in modern industry and society. However, the reconstruction of featured CAD model is more challenging than the reconstruction of other CAD models. To this end, this paper proposes an end-to-end network to reconstruct featured CAD model from point cloud (P2CADNet). Initially, the proposed P2CADNet architecture combines a point cloud feature extractor, a CAD sequence reconstructor and a parameter optimizer. Subsequently, in order to reconstruct the featured CAD model in an autoregressive way, the CAD sequence reconstructor applies two transformer decoders, one with target mask and the other without mask. Finally, for predicting parameters more precisely, we design a parameter optimizer with cross-attention mechanism to further refine the CAD feature parameters. We evaluate P2CADNet on the public dataset, and the experimental results show that P2CADNet has excellent reconstruction quality and accuracy. To our best knowledge, P2CADNet is the first end-to-end network to reconstruct featured CAD model from point cloud, and can be regarded as baseline for future works. Therefore, we open the source code at https://github.com/Blice0415/P2CADNet.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. CAD-CAM technology: a literature review. Al-Rafidain Dental Journal, 20(1): 95–113.
  2. Parametric CAD modeling: An analysis of strategies for design reusability. Computer-Aided Design, 74: 18–31.
  3. Computer-Aided Design, Computer-Aided Engineering, and Visualization. In Springer Handbook of Automation, 641–659. Springer.
  4. MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth. Transactions on Machine Learning Research.
  5. ShapeNet: An Information-Rich 3D Model Repository. Technical Report arXiv:1512.03012 [cs.GR], Stanford University — Princeton University — Toyota Technological Institute at Chicago.
  6. Inversecsg: Automatic conversion of 3d models to csg trees. ACM Transactions on Graphics (TOG), 37(6): 1–16.
  7. A Point Set Generation Network for 3D Object Reconstruction From a Single Image. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 605–613.
  8. A Survey of Methods for Converting Unstructured Data to CSG Models. arXiv preprint arXiv:2305.01220.
  9. Computer-aided design as language. Advances in Neural Information Processing Systems, 34: 5885–5897.
  10. Complexgen: Cad reconstruction by b-rep chain complex generation. ACM Transactions on Graphics (TOG), 41(4): 1–18.
  11. Surface Reconstruction from Point Clouds: A Survey and a Benchmark. arXiv:2205.02413.
  12. Solidgen: An autoregressive model for direct b-rep synthesis. arXiv preprint arXiv:2203.13944.
  13. Self-Supervised Representation Learning for CAD. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 21327–21336.
  14. UCSG-NET-unsupervised discovering of constructive solid geometry tree. Advances in Neural Information Processing Systems, 33: 8776–8786.
  15. ABC: A Big CAD Model Dataset for Geometric Deep Learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9601–9611.
  16. Advances in CAD/CAM/CAE Technologies. Machines, 8(1).
  17. Reconstructing Editable Prismatic CAD from Rounded Voxel Models. In SIGGRAPH Asia 2022 Conference Papers, SA ’22. New York, NY, USA: Association for Computing Machinery. ISBN 9781450394703.
  18. XVoxel-Based Parametric Design Optimization of Feature Models. Computer-Aided Design, 160: 103528.
  19. Neural Reflectance Decomposition Under Dynamic Point Light. IEEE Transactions on Circuits and Systems for Video Technology, 1–1.
  20. Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1).
  21. Feature-Based Reconstruction of Non-Beam-Like Topology Optimization Design Proposals in Boundary-Representation. In DS 119: Proceedings of the 33rd Symposium Design for X (DFX2022), 1–10.
  22. Occupancy Networks: Learning 3D Reconstruction in Function Space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4460–4470.
  23. Cutting guides in Mandibular Tumor Ablation: Are We as Accurate as We Think? Journal of Oral and Maxillofacial Surgery, 80(9): S73.
  24. Rapidly finding CAD features using database optimization. Computer-Aided Design, 69: 35–50.
  25. Graphical Representation of Parametric Feature-Based MCAD Model Characteristics. Computer-Aided Design and Applications, 20(2).
  26. JointMETRO: a 3D reconstruction model for human figures in works of art based on transformer. Neural Computing and Applications, 1–15.
  27. Reverse engineering of CAD models via clustering and approximate implicitization. Computer Aided Geometric Design, 80: 101876.
  28. Csg-stump: A learning friendly csg-like representation for interpretable shape parsing. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 12478–12487.
  29. Incremental reconstruction of planar B-Rep models from multiple point clouds. The Visual Computer: International Journal of Computer Graphics, 32(6-8): 945–954.
  30. Feature-Based Object Detection and Pose Estimation Based on 3D Cameras and CAD Models for Industrial Robot Applications. In 2022 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA), 1–5. IEEE.
  31. Csgnet: Neural shape parser for constructive solid geometry. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5515–5523.
  32. Neural Shape Parsers for Constructive Solid Geometry. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(5): 2628–2640.
  33. CLUSTERING OF SEQUENTIAL CAD MODELLING DATA. Proceedings of the Design Society, 3: 937–946.
  34. Building editable B-Rep models from unorganized point clouds. Jul, 7: 1–10.
  35. NeuralRecon: Real-time coherent 3D reconstruction from monocular video. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 15598–15607.
  36. Pixel2Mesh: 3D Mesh Model Generation via Image Guided Deformation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(10): 3600–3613.
  37. 3D Shape Reconstruction From 2D Images With Disentangled Attribute Flow. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 3803–3813.
  38. Multi-View Mesh Reconstruction With Neural Deferred Shading. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 6187–6197.
  39. DeepCAD: A Deep Generative Network for Computer-Aided Design Models. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 6772–6782.
  40. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1912–1920.
  41. Mvsnet: Depth inference for unstructured multi-view stereo. In Proceedings of the European conference on computer vision (ECCV), 767–783.
  42. Recurrent mvsnet for high-resolution multi-view stereo depth inference. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 5525–5534.
  43. Topologically robust CAD model generation for structural optimisation. Computer Methods in Applied Mechanics and Engineering, 369: 113102.
  44. Learning To Recover 3D Scene Shape From a Single Image. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 204–213.
  45. Feature-based modeling for variable fractal geometry design integrated into CAD system. Advanced Engineering Informatics, 57: 102006.

Summary

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

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