Label-Guided Generative Adversarial Network for Realistic Image Synthesis

Generating photo-realistic images from labels (e.g., semantic labels or sketch labels) is much more challenging than the general image-to-image translation task, mainly due to the large differences between extremely sparse labels and detail rich images. We propose a general framework Lab2Pix to tack...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 3 vom: 28. März, Seite 3311-3328
1. Verfasser: Zhu, Junchen (VerfasserIn)
Weitere Verfasser: Gao, Lianli, Song, Jingkuan, Li, Yuan-Fang, Zheng, Feng, Li, Xuelong, Shen, Heng Tao
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article