SolidGen: An Autoregressive Model for Direct B-rep Synthesis

TL;DR

SolidGen is a novel autoregressive neural network that directly synthesizes boundary representations (B-reps) for CAD models, eliminating the need for sequence-based supervision and enabling conditioned generation.

Contribution

We introduce SolidGen, a Transformer-based model that directly generates B-reps using an Indexed Boundary Representation, advancing CAD model synthesis without supervision.

Findings

SolidGen produces high-quality, realistic CAD models.

The model effectively conditions on various contexts like labels and images.

Quantitative and perceptual evaluations confirm its superiority.

Abstract

The Boundary representation (B-rep) format is the de-facto shape representation in computer-aided design (CAD) to model solid and sheet objects. Recent approaches to generating CAD models have focused on learning sketch-and-extrude modeling sequences that are executed by a solid modeling kernel in postprocess to recover a B-rep. In this paper we present a new approach that enables learning from and synthesizing B-reps without the need for supervision through CAD modeling sequence data. Our method SolidGen, is an autoregressive neural network that models the B-rep directly by predicting the vertices, edges, and faces using Transformer-based and pointer neural networks. Key to achieving this is our Indexed Boundary Representation that references B-rep vertices, edges and faces in a well-defined hierarchy to capture the geometric and topological relations suitable for use with machine learning. SolidGen can be easily conditioned on contexts e.g., class labels, images, and voxels thanks to its probabilistic modeling of the B-rep distribution. We demonstrate qualitatively, quantitatively, and through perceptual evaluation by human subjects that SolidGen can produce high quality, realistic CAD models.