A Method for Animating Children's Drawings of the Human Figure

TL;DR

This paper introduces a robust, user-friendly system for automatically animating children's drawings of human figures, supported by a large dataset and a publicly accessible demo that has reached millions worldwide.

Contribution

It presents a novel method for animating children's drawings, introduces the Amateur Drawings Dataset, and demonstrates the system's effectiveness through experiments and a perceptual study.

Findings

The system is robust to variance in children's drawings.

The public demo has been used by millions globally.

The dataset contains over 178,000 annotated amateur drawings.

Abstract

Children's drawings have a wonderful inventiveness, creativity, and variety to them. We present a system that automatically animates children's drawings of the human figure, is robust to the variance inherent in these depictions, and is simple and straightforward enough for anyone to use. We demonstrate the value and broad appeal of our approach by building and releasing the Animated Drawings Demo, a freely available public website that has been used by millions of people around the world. We present a set of experiments exploring the amount of training data needed for fine-tuning, as well as a perceptual study demonstrating the appeal of a novel twisted perspective retargeting technique. Finally, we introduce the Amateur Drawings Dataset, a first-of-its-kind annotated dataset, collected via the public demo, containing over 178,000 amateur drawings and corresponding user-accepted character bounding boxes, segmentation masks, and joint location annotations.