Publication | ACM SIGGRAPH Asia – Technical Briefs Program 2022

Reconstructing editable prismatic CAD from rounded voxel models

This paper describes a system for generating a CAD model with parametric history which approximates a target shape defined in a voxel grid. The sketches in the history contain appropriate constraints and dimensions, making the geometry easy to edit with existing CAD applications.

Unlike other approaches, this work implements a simple CAD modeler for axis aligned extrusions using the tensors of the machine learning framework. The decomposition of the input model into extrusions, and the recombination of these extrusions is hence end to end differentiable, allowing the definition of a geometry aware loss function. The paper shows that this approach provides better approximations to the target shape than other methods.

Download publication

Abstract

Reconstructing editable prismatic CAD from rounded voxel models

Joseph George Lambourne, Karl D.D. Willis, Pradeep Kumar Jayaraman, Longfei Zhang, Aditya Sanghi, Kamal Rahimi Malekshan

ACM SIGGRAPH Asia – Technical Briefs Program 2022

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.

Related Resources

Publication

2024

SolidGen: An Autoregressive Model for Direct B-rep Synthesis

A generative model that can synthesize 3D CAD models in the boundary…

Publication

2021

BRepNet: A topological message passing system for solid models

Boundary representation (B-rep) models are the standard way 3D shapes…

Publication

2022

JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints

Physical products are often complex assemblies combining a multitude…

Publication

2021

UV-Net: Learning from Boundary Representations

We introduce UV-Net, a novel neural network architecture and…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us