Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction

• URL: http://arxiv.org/abs/2505.02043v2
• Date: Tue, 20 May 2025 14:23:48 GMT
• Title: Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction
• Authors: Cheng Wang, Xinzhu Ma, Bin Wang, Shixiang Tang, Yuan Meng, Ping Jiang,
• Abstract summary: We propose a CAD reconstruction network that produces editable CAD models from input point clouds (Point2Primitive)<n>Point2Primitive can directly detect and predict sketch curves (type and parameter) from point clouds based on an improved transformer.
• Score: 21.252463825836497
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recovering CAD models from point clouds, especially the sketch-extrusion process, can be seen as the process of rebuilding the topology and extrusion primitives. Previous methods utilize implicit fields for sketch representation, leading to shape reconstruction of curved edges. In this paper, we proposed a CAD reconstruction network that produces editable CAD models from input point clouds (Point2Primitive) by directly predicting every element of the extrusion primitives. Point2Primitive can directly detect and predict sketch curves (type and parameter) from point clouds based on an improved transformer. The sketch curve parameters are formulated as position queries and optimized in an autoregressive way, leading to high parameter accuracy. The topology is rebuilt by extrusion segmentation, and each extrusion parameter (sketch and extrusion operation) is recovered by combining the predicted curves and the computed extrusion operation. Extensive experiments demonstrate that our method is superior in primitive prediction accuracy and CAD reconstruction. The reconstructed shapes are of high geometrical fidelity.

Related papers

• Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformation [50.26314343851213]
  Inferring signed distance functions (SDFs) from sparse point clouds remains a challenge in surface reconstruction.<n>We present a novel approach that learns a dynamic deformation network to predict SDFs in an end-to-end manner.<n> Experimental results on synthetic and real scanned datasets demonstrate that our method significantly outperforms the current state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-31T02:27:02Z)
• OffsetOPT: Explicit Surface Reconstruction without Normals [7.297352404640493]
  We propose OffsetOPT, a method that reconstructs explicit surfaces directly from 3D point clouds.<n>We demonstrate its accuracy on popular benchmarks, including small-scale shapes and large-scale open surfaces.
  arXiv  Detail & Related papers  (2025-03-20T00:47:27Z)
• 3D Neural Edge Reconstruction [61.10201396044153]
  We introduce EMAP, a new method for learning 3D edge representations with a focus on both lines and curves. Our method implicitly encodes 3D edge distance and direction in Unsigned Distance Functions (UDF) from multi-view edge maps. On top of this neural representation, we propose an edge extraction algorithm that robustly abstracts 3D edges from the inferred edge points and their directions.
  arXiv  Detail & Related papers  (2024-05-29T17:23:51Z)
• PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstruction [86.726941702182]
  We introduce geometric guidance into the reconstruction network PS-CAD. We provide the geometry of surfaces where the current reconstruction differs from the complete model as a point cloud. Second, we use geometric analysis to extract a set of planar prompts, that correspond to candidate surfaces.
  arXiv  Detail & Related papers  (2024-05-24T03:43:55Z)
• NeurCADRecon: Neural Representation for Reconstructing CAD Surfaces by Enforcing Zero Gaussian Curvature [42.39976072777987]
  High-fidelity reconstruction of a CAD model from low-quality unoriented point clouds remains a significant challenge. In this paper, we address this challenge based on the prior observation that the surface of a CAD model is generally composed of piecewise surface patches. Our approach, named NeurCADRecon, is self-supervised and its loss includes a developability term to encourage the Gaussian curvature toward 0.
  arXiv  Detail & Related papers  (2024-04-20T16:36:24Z)
• ParaPoint: Learning Global Free-Boundary Surface Parameterization of 3D Point Clouds [52.03819676074455]
  ParaPoint is an unsupervised neural learning pipeline for achieving global free-boundary surface parameterization. This work makes the first attempt to investigate neural point cloud parameterization that pursues both global mappings and free boundaries.
  arXiv  Detail & Related papers  (2024-03-15T14:35:05Z)
• Reconstructing editable prismatic CAD from rounded voxel models [16.03976415868563]
  We introduce a novel neural network architecture to solve this challenging task. Our method reconstructs the input geometry in the voxel space by decomposing the shape. During inference, we obtain the CAD data by first searching a database of 2D constrained sketches.
  arXiv  Detail & Related papers  (2022-09-02T16:44:10Z)
• Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders [25.389088434370066]
  We propose Point2Cyl, a supervised network transforming a raw 3D point cloud to a set of extrusion cylinders. Our approach demonstrates the best performance on two recent CAD datasets.
  arXiv  Detail & Related papers  (2021-12-17T05:22:28Z)
• Cloud2Curve: Generation and Vectorization of Parametric Sketches [109.02932608241227]
  We present Cloud2Curve, a generative model for scalable high-resolution vector sketches. We evaluate the generation and vectorization capabilities of our model on Quick, Draw! and KMNIST datasets.
  arXiv  Detail & Related papers  (2021-03-29T12:09:42Z)
• Quantization in Relative Gradient Angle Domain For Building Polygon Estimation [88.80146152060888]
  CNN approaches often generate imprecise building morphologies including noisy edges and round corners. We propose a module that uses prior knowledge of building corners to create angular and concise building polygons from CNN segmentation outputs. Experimental results demonstrate that our method refines CNN output from a rounded approximation to a more clear-cut angular shape of the building footprint.
  arXiv  Detail & Related papers  (2020-07-10T21:33:06Z)
• Anomaly Detection and Prototype Selection Using Polyhedron Curvature [12.323996999894002]
  We propose a novel approach to anomaly detection called Curvature Anomaly Detection (CAD) and Kernel CAD. Our experiments on different benchmarks show that the proposed methods are effective for anomaly detection and prototype selection.
  arXiv  Detail & Related papers  (2020-04-05T09:50:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.