PaintsTorch: a User-Guided Anime Line Art Colorization Tool with Double Generator Conditional Adversarial Network - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

PaintsTorch: a User-Guided Anime Line Art Colorization Tool with Double Generator Conditional Adversarial Network

Résumé

The lack of information provided by line arts makes user guidedcolorization a challenging task for computer vision. Recent contributions from the deep learning community based on Generative Adversarial Network (GAN) have shown incredible results compared to previous techniques. These methods employ user input color hints as a way to condition the network. The current state of the art has shown the ability to generalize and generate realistic and precise colorization by introducing a custom dataset and a new model with its training pipeline. Nevertheless, their approach relies on randomly sampled pixels as color hints for training. Thus, in this contribution, we introduce a stroke simulation based approach for hint generation, making the model more robust to messy inputs. We also propose a new cleaner dataset, and explore the use of a double generator GAN to improve visual fidelity.
Fichier principal
Vignette du fichier
PaintsTorch.pdf (12.15 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02455373 , version 1 (09-12-2020)

Identifiants

Citer

Yliess Hati, Gregor Jouet, Francis Rousseaux, Clément Duhart. PaintsTorch: a User-Guided Anime Line Art Colorization Tool with Double Generator Conditional Adversarial Network. European Conference on Visual Media Production (CVMP), 2019, Londres, United Kingdom. pp.1-10, ⟨10.1145/3359998.3369401⟩. ⟨hal-02455373⟩
205 Consultations
115 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More