“Abstraction-Perception Preserving Cartoon Face Synthesis”, 2023-03-22 ():
Portrait cartoonization aims at translating a portrait image to its cartoon version, which guarantees two conditions, namely, reducing textural details and synthesizing cartoon facial features (eg. big eyes or line-drawing nose).
To address this problem, we propose a two-stage training scheme based on GAN, which is powerful for stylization problems.
The abstraction stage with a novel abstractive loss is used to reduce textural details. Meanwhile, the perception stage is adopted to synthesize cartoon facial features.
To comprehensively evaluate the proposed method and other state-of-the-art methods for portrait cartoonization, we contribute a new challenging large-scale dataset named CartoonFace10K…we access the website of Anime-Planet to collect 50,245 images of cartoon characters. We use gender filter for separately collecting male and female characters. Secondly, a cartoon facial detector is leveraged to remove non-human images, eg. the character of Doraemon or Pikachu. Following the removal stage, there are 14,021 cartoon human face images. To enhance the confidence, we do a manual check across all images to ensure the purity of our proposed dataset. [They don’t explain why Danbooru Portraits or one of the many other face-crop datasets wouldn’t’ve worked…]
In addition, we find that the popular metric FID focuses on the target style yet ignores the preservation of the input image content. We thus introduce a novel metric FISI, which compromises FID and SSIM to focus on both target features and retaining input content.
Quantitative and qualitative results demonstrate that our proposed method outperforms other state-of-the-art methods.