DAVINCI: A Single-Stage Architecture for Constrained CAD Sketch Inference

TL;DR

DAVINCI is a novel single-stage neural architecture that jointly infers CAD sketch parameters and constraints directly from raster images, achieving state-of-the-art results and reducing data requirements through innovative augmentation techniques.

Contribution

Introduces DAVINCI, a unified model for CAD sketch inference, and proposes CPTs for data augmentation, significantly reducing the need for large annotated datasets.

Findings

Achieves state-of-the-art performance on SketchGraphs dataset.

Effective even with only 0.1% of training data using CPTs.

Provides a new CPT-augmented SketchGraphs dataset with 80 million sketches.

Abstract

This work presents DAVINCI, a unified architecture for single-stage Computer-Aided Design (CAD) sketch parameterization and constraint inference directly from raster sketch images. By jointly learning both outputs, DAVINCI minimizes error accumulation and enhances the performance of constrained CAD sketch inference. Notably, DAVINCI achieves state-of-the-art results on the large-scale SketchGraphs dataset, demonstrating effectiveness on both precise and hand-drawn raster CAD sketches. To reduce DAVINCI's reliance on large-scale annotated datasets, we explore the efficacy of CAD sketch augmentations. We introduce Constraint-Preserving Transformations (CPTs), i.e. random permutations of the parametric primitives of a CAD sketch that preserve its constraints. This data augmentation strategy allows DAVINCI to achieve reasonable performance when trained with only 0.1% of the SketchGraphs dataset. Furthermore, this work contributes a new version of SketchGraphs, augmented with CPTs. The newly introduced CPTSketchGraphs dataset includes 80 million CPT-augmented sketches, thus providing a rich resource for future research in the CAD sketch domain.