Reconstructing editable prismatic CAD from rounded voxel models
arXiv:2209.01161 · doi:10.1145/3550469.3555424
Abstract
Reverse Engineering a CAD shape from other representations is an important geometric processing step for many downstream applications. In this work, we introduce a novel neural network architecture to solve this challenging task and approximate a smoothed signed distance function with an editable, constrained, prismatic CAD model. During training, our method reconstructs the input geometry in the voxel space by decomposing the shape into a series of 2D profile images and 1D envelope functions. These can then be recombined in a differentiable way allowing a geometric loss function to be defined. During inference, we obtain the CAD data by first searching a database of 2D constrained sketches to find curves which approximate the profile images, then extrude them and use Boolean operations to build the final CAD model. Our method approximates the target shape more closely than other methods and outputs highly editable constrained parametric sketches which are compatible with existing CAD software.
arXiv commentSIGGRAPH Asia 2022 Conference Paper
References in corpus (14)
- Supervised Fitting of Geometric Primitives to 3D Point Clouds
- Learning to Infer and Execute 3D Shape Programs
- PolyGen: An Autoregressive Generative Model of 3D Meshes
- Synthesizing Structured CAD Models with Equality Saturation and Inverse Transformations
- PIE-NET: Parametric Inference of Point Cloud Edges
- Computer-Aided Design as Language
- UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Tree
- SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design
- SketchGen: Generating Constrained CAD Sketches
- Write, Execute, Assess: Program Synthesis with a REPL
- SolidGen: An Autoregressive Model for Direct B-rep Synthesis
- Implicit Conversion of Manifold B-Rep Solids by Neural Halfspace Representation
- Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequences
- ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generation