CAD2Sketch: Generating Concept Sketches from CAD Sequences

Felix Hähnlein Université Côte d'Azur, Inria
Changjian Li Université Côte d'Azur, Inria
Niloy J. Mitra University College London, Adobe Research
Adrien Bousseau Université Côte d'Azur, Inria
SIGGRAPH Asia 2022

[Paper]

We introduce CAD2Sketch to synthesize concept sketches directly from CAD sequences. Our work focuses on reducing the domain gap between freehand concept sketches and synthetically generated ones. We achieve this by focusing on generating intermediate lines (i.e., scaffold and auxiliary construction lines used by artists to reduce errors in ‘sighting’ perspective effects) and by recreating drawing style to reflect importance of lines. Here we show three real-world sketches and three synthetic sketches generated with our approach. Can you tell them apart?

Abstract

Concept sketches are ubiquitous in industrial design, as they allow designers to quickly depict imaginary 3D objects. To construct their sketches with accurate perspective, designers rely on longstanding drawing techniques, including the use of auxiliary construction lines to identify midpoints of perspective planes, to align points vertically and horizontally, and to project planar curves from one perspective plane to another. We present a method to synthesize such construction lines from CAD sequences. Importantly, our method balances the presence of construction lines with overall clutter, such that the resulting sketch is both well-constructed and readable, as professional designers are trained to do. In addition to generating sketches that are visually similar to real ones, we apply our method to synthesize a large quantity of paired sketches and normal maps, and show that the resulting dataset can be used to train a neural network to infer normals from concept sketches.

Code

The code for the paper.

Data