SOTAVerified

Diffusart: Enhancing Line Art Colorization with Conditional Diffusion Models

2023-06-18Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2023Code Available1· sign in to hype

Hernan Carrillo, Michaël Clément, Aurélie Bugeau, Edgar Simo-Serra

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Colorization of line art drawings is an important task in illustration and animation workflows. However, this highly laborious process is mainly done manually, limiting the creative productivity. This paper presents a novel interactive approach for line art colorization using conditional Diffusion Probabilistic Models (DPMs). In our proposed approach, the user provides initial color strokes for colorizing the line art. The strokes are then integrated into the conditional DPM-based colorization process by means of a coupled implicit and explicit conditioning strategy to generates diverse and high-quality colorized images. We evaluate our proposal and show it outperforms existing state-of-the-art approaches using the FID, LPIPS and SSIM metrics.

Tasks

Reproductions