Controllable multi-domain semantic artwork synthesis

Abstract We present a novel framework for the multi-domain synthesis of artworks from semantic layouts. One of the main limitations of this challenging task is the lack of publicly available segmentation datasets for art synthesis. To address this problem, we propose a dataset called ArtSem that con...

Cijeli opis

Bibliografski detalji

Glavni autori:	Yuantian Huang, Satoshi Iizuka, Edgar Simo-Serra, Kazuhiro Fukui
Format:	Artigo
Jezik:	Inglês
Izdano:	Tsinghua University Press 2024-01-01
Serija:	Computational Visual Media
Teme:	semantic artwork synthesis generative adversarial network (GAN) datasets non-photorealistic rendering
Online pristup:	https://doi.org/10.1007/s41095-023-0356-2
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!