Diffusart: Enhancing Line Art Colorization with Conditional Diffusion Models - Archive ouverte HAL
Communication Dans Un Congrès Année : 2023

Diffusart: Enhancing Line Art Colorization with Conditional Diffusion Models

Résumé

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.
Fichier principal
Vignette du fichier
01-3.pdf (1.88 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04094357 , version 1 (10-05-2023)

Identifiants

  • HAL Id : hal-04094357 , version 1

Citer

Hernan Carrillo, Michaël Clément, Aurélie Bugeau, Edgar Simo-Serra. Diffusart: Enhancing Line Art Colorization with Conditional Diffusion Models. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Jun 2023, Vancouver, Canada. ⟨hal-04094357⟩

Collections

CNRS ANR
54 Consultations
124 Téléchargements

Partager

More