APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs

By Ran Yi, Yong-jin Liu, Yu-Kun Lai, Paul L. Rosin. 2019

176 citations recorded by the source corpus.

Significant progress has been made with image stylization using deep learning, especially with generative adversarial networks (GANs). However, existing methods fail to produce high quality artistic portrait drawings. Such drawings have a highly abstract style, containing a sparse set of continuous graphical elements such as lines, and so small artifacts are much more exposed than for painting styles. Moreover, artists tend to use different strategies to draw different facial features and the lines drawn are only loosely related to obvious image features. To address these challenges, we propose APDrawingGAN, a novel GAN based architecture that builds upon hierarchical generators and discriminators combining both a global network (for images as a whole) and local networks (for individual facial regions). This allows dedicated drawing strategies to be learned for different facial features. Since artists' drawings may not have lines perfectly aligned with image features, we develop a novel loss to measure similarity between generated and artists' drawings based on distance transforms, leading to improved strokes in portrait drawing. To train APDrawingGAN, we construct an artistic drawing dataset containing high-resolution portrait photos and corresponding professional artistic drawings. Extensive experiments, including a user study, show that APDrawingGAN produces significantly better artistic drawings than state-of-the-art methods.

Subfields: Cognitive Neuroscience, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

1. Dacheng Tao
2. Baoyuan Wu
3. Jie Gui
4. Jieping Ye
5. Lu Yuan
6. Yonggang Wen
7. Fang Wen
8. Zhenan Sun

In Computer Graphics and Computer-Aided Design

1. Dacheng Tao
2. Baoyuan Wu
3. Lu Yuan
4. Bo Zhang
5. Fang Wen
6. Zhenan Sun
7. Jing-Hao Xue
8. Yujiu Yang

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Xiaogang Wang
3. Ming-Hsuan Yang
4. Luc Van Gool
5. Xiaoou Tang
6. Lu Yuan
7. Yujiu Yang
8. Weihao Xia

In Generative Models

1. Yujiu Yang
2. Weihao Xia
3. Jing-Hao Xue
4. Dong Chen
5. Bo Zhang
6. Dacheng Tao
7. Baoyuan Wu
8. Jie Gui

Citations in the corpus

• Towards Open-World Text-Guided Face Image Generation and Manipulation (2021, methodology): “, images from other face dataset such as [66], [67], [68], which illustrate that our method is prepared to produce pleasing results for the in-the-wild images.”
• TediGAN: Text-Guided Diverse Face Image Generation and Manipulation (2021, methodology): “The images in last two columns are results of out-of-distribution (Non-CelebA), i.e. , images from other face dataset such as [4, 6, 41], which illustrate that our method is prepared to produce pleasing results with images in the wild.”
• TediGAN: Text-Guided Diverse Image Generation and Manipulation (2020, methodology): “, images from other face dataset such as [4, 8, 55], which illustrate that our method is prepared to produce pleasing results with images in the wild.”
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications (2020, background): “Portrait Related: APDrawingGAN [60] was proposed to generate artistic portrait drawings from face photos with”
• Cross-Domain Correspondence Learning for Exemplar-Based Image Translation (2020, methodology): “In order to consider the mask (or edge) in the training, some methods [10, 46, 5] explicitly separate the exemplar image into semantic regions and learns to synthesize different parts individually.”