Diffutoon: High-Resolution Editable Toon Shading via Diffusion Models
This work addresses the challenge of maintaining consistency and visual quality in video stylization for animation and non-photorealistic rendering applications, representing an incremental improvement over existing methods.
The paper tackled the problem of video toon shading, which converts photorealistic videos into anime styles, by proposing Diffutoon, a diffusion-based method that achieves high-resolution, consistent, and editable stylization, outperforming existing baselines in quantitative metrics and human evaluations.
Toon shading is a type of non-photorealistic rendering task of animation. Its primary purpose is to render objects with a flat and stylized appearance. As diffusion models have ascended to the forefront of image synthesis methodologies, this paper delves into an innovative form of toon shading based on diffusion models, aiming to directly render photorealistic videos into anime styles. In video stylization, extant methods encounter persistent challenges, notably in maintaining consistency and achieving high visual quality. In this paper, we model the toon shading problem as four subproblems: stylization, consistency enhancement, structure guidance, and colorization. To address the challenges in video stylization, we propose an effective toon shading approach called \textit{Diffutoon}. Diffutoon is capable of rendering remarkably detailed, high-resolution, and extended-duration videos in anime style. It can also edit the content according to prompts via an additional branch. The efficacy of Diffutoon is evaluated through quantitive metrics and human evaluation. Notably, Diffutoon surpasses both open-source and closed-source baseline approaches in our experiments. Our work is accompanied by the release of both the source code and example videos on Github (Project page: https://ecnu-cilab.github.io/DiffutoonProjectPage/).