View2CAD: Reconstructing View-Centric CAD Models from Single RGB-D Scans

• URL: http://arxiv.org/abs/2504.04000v1
• Date: Sat, 05 Apr 2025 00:10:50 GMT
• Title: View2CAD: Reconstructing View-Centric CAD Models from Single RGB-D Scans
• Authors: James Noeckel, Benjamin Jones, Adriana Schulz, Brian Curless,
• Abstract summary: Parametric CAD models, represented as Boundary Representations (B-reps), are foundational to modern design and manufacturing.<n>Existing methods to recover B-Reps from measured data require complete, noise-free 3D data.<n>We propose a method that addresses the challenge of reconstructing only the observed geometry from a single view.
• Score: 9.043106675778303
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Parametric CAD models, represented as Boundary Representations (B-reps), are foundational to modern design and manufacturing workflows, offering the precision and topological breakdown required for downstream tasks such as analysis, editing, and fabrication. However, B-Reps are often inaccessible due to conversion to more standardized, less expressive geometry formats. Existing methods to recover B-Reps from measured data require complete, noise-free 3D data, which are laborious to obtain. We alleviate this difficulty by enabling the precise reconstruction of CAD shapes from a single RGB-D image. We propose a method that addresses the challenge of reconstructing only the observed geometry from a single view. To allow for these partial observations, and to avoid hallucinating incorrect geometry, we introduce a novel view-centric B-rep (VB-Rep) representation, which incorporates structures to handle visibility limits and encode geometric uncertainty. We combine panoptic image segmentation with iterative geometric optimization to refine and improve the reconstruction process. Our results demonstrate high-quality reconstruction on synthetic and real RGB-D data, showing that our method can bridge the reality gap.

Related papers

• DiMeR: Disentangled Mesh Reconstruction Model [24.07380724530745]
  We introduce DiMeR, a novel disentangled dual-stream feed-forward model for sparse-view mesh reconstruction. We demonstrate robust capabilities across various tasks, including sparse-view reconstruction, single-image-to-3D, and text-to-3D.
  arXiv  Detail & Related papers  (2025-04-24T15:39:20Z)
• CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images [69.7768227804928]
  CADCrafter is an image-to-parametric CAD model generation framework that trains solely on synthetic textureless CAD data.<n>We introduce a geometry encoder to accurately capture diverse geometric features.<n>Our approach can robustly handle real unconstrained CAD images, and even generalize to unseen general objects.
  arXiv  Detail & Related papers  (2025-04-07T06:01:35Z)
• Hyperbolic-constraint Point Cloud Reconstruction from Single RGB-D Images [19.23499128175523]
  We introduce hyperbolic space to 3D point cloud reconstruction, enabling the model to represent and understand complex hierarchical structures in point clouds with low distortion.<n>Our model outperforms most existing models, and ablation studies demonstrate the significance of our model and its components.
  arXiv  Detail & Related papers  (2024-12-12T08:27:39Z)
• BRep Boundary and Junction Detection for CAD Reverse Engineering [14.662769071664252]
  In machining process, 3D reverse engineering of the mechanical system is an integral, highly important, and yet time consuming step. Deep learning-based Scan-to-CAD modeling can offer designers enormous editability to quickly modify CAD model. We propose a supervised boundary representation (BRep) detection network BRepDetNet from 3D scans of CC3D and ABC dataset.
  arXiv  Detail & Related papers  (2024-09-21T09:53:11Z)
• 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)
• DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Image [34.47379913018661]
  We propose DiffCAD, the first weakly-supervised probabilistic approach to CAD retrieval and alignment from an RGB image. We formulate this as a conditional generative task, leveraging diffusion to learn implicit probabilistic models capturing the shape, pose, and scale of CAD objects in an image. Our approach is trained only on synthetic data, leveraging monocular depth and mask estimates to enable robust zero-shot adaptation to various real target domains.
  arXiv  Detail & Related papers  (2023-11-30T15:10:21Z)
• U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds [84.32525852378525]
  We propose U-RED, an Unsupervised shape REtrieval and Deformation pipeline. It takes an arbitrary object observation as input, typically captured by RGB images or scans, and jointly retrieves and deforms the geometrically similar CAD models. We show that U-RED surpasses existing state-of-the-art approaches by 47.3%, 16.7% and 31.6% respectively under Chamfer Distance.
  arXiv  Detail & Related papers  (2023-08-11T20:56:05Z)
• 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)
• Single-view 3D Mesh Reconstruction for Seen and Unseen Categories [69.29406107513621]
  Single-view 3D Mesh Reconstruction is a fundamental computer vision task that aims at recovering 3D shapes from single-view RGB images. This paper tackles Single-view 3D Mesh Reconstruction, to study the model generalization on unseen categories. We propose an end-to-end two-stage network, GenMesh, to break the category boundaries in reconstruction.
  arXiv  Detail & Related papers  (2022-08-04T14:13:35Z)
• Multi-view 3D Reconstruction of a Texture-less Smooth Surface of Unknown Generic Reflectance [86.05191217004415]
  Multi-view reconstruction of texture-less objects with unknown surface reflectance is a challenging task. This paper proposes a simple and robust solution to this problem based on a co-light scanner.
  arXiv  Detail & Related papers  (2021-05-25T01:28:54Z)
• From Points to Multi-Object 3D Reconstruction [71.17445805257196]
  We propose a method to detect and reconstruct multiple 3D objects from a single RGB image. A keypoint detector localizes objects as center points and directly predicts all object properties, including 9-DoF bounding boxes and 3D shapes. The presented approach performs lightweight reconstruction in a single-stage, it is real-time capable, fully differentiable and end-to-end trainable.
  arXiv  Detail & Related papers  (2020-12-21T18:52:21Z)

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.