Can I teach a robot to replicate a line art

TL;DR

This paper introduces a novel pipeline enabling robots to replicate line art by converting grayscale sketches into stroke sequences, demonstrating high accuracy and better generalization than rule-based methods.

Contribution

The paper presents a new task of mimicking line drawings, a modified dataset for supervised training, and a multi-stage segmentation pipeline for robotic replication of line art.

Findings

Achieved around 98% accuracy on the Quick-draw dataset.

Outperformed baseline architectures significantly.

Generalized well to complex sketches, unlike rule-based methods.

Abstract

Line art is arguably one of the fundamental and versatile modes of expression. We propose a pipeline for a robot to look at a grayscale line art and redraw it. The key novel elements of our pipeline are: a) we propose a novel task of mimicking line drawings, b) to solve the pipeline we modify the Quick-draw dataset to obtain supervised training for converting a line drawing into a series of strokes c) we propose a multi-stage segmentation and graph interpretation pipeline for solving the problem. The resultant method has also been deployed on a CNC plotter as well as a robotic arm. We have trained several variations of the proposed methods and evaluate these on a dataset obtained from Quick-draw. Through the best methods we observe an accuracy of around 98% for this task, which is a significant improvement over the baseline architecture we adapted from. This therefore allows for deployment of the method on robots for replicating line art in a reliable manner. We also show that while the rule-based vectorization methods do suffice for simple drawings, it fails for more complicated sketches, unlike our method which generalizes well to more complicated distributions.