Sketch-Inspector: a Deep Mixture Model for High-Quality Sketch Generation of Cats

TL;DR

This paper introduces a deep mixture model with CNN components to generate high-quality, recognizable cat sketches, outperforming previous models like Sketch-RNN in producing more accurate and detailed sketches.

Contribution

A novel sketch generation system using CNN predictors and discriminators to improve the recognizability and quality of AI-generated sketches, focusing on cats from the QuickDraw dataset.

Findings

Generated sketches are more recognizable than previous models.

Model outperforms Sketch-RNN in sketch quality.

Produced sketches surpass human-drawn quality.

Abstract

With the involvement of artificial intelligence (AI), sketches can be automatically generated under certain topics. Even though breakthroughs have been made in previous studies in this area, a relatively high proportion of the generated figures are too abstract to recognize, which illustrates that AIs fail to learn the general pattern of the target object when drawing. This paper posits that supervising the process of stroke generation can lead to a more accurate sketch interpretation. Based on that, a sketch generating system with an assistant convolutional neural network (CNN) predictor to suggest the shape of the next stroke is presented in this paper. In addition, a CNN-based discriminator is introduced to judge the recognizability of the end product. Since the base-line model is ineffective at generating multi-class sketches, we restrict the model to produce one category. Because the image of a cat is easy to identify, we consider cat sketches selected from the QuickDraw data set. This paper compares the proposed model with the original Sketch-RNN on 75K human-drawn cat sketches. The result indicates that our model produces sketches with higher quality than human's sketches.