Freestyle Layout-to-Image Synthesis

Xue, H; Huang, ZW; Sun, QR; Song, L; Zhang, WJ

Xue, H (通讯作者),Shanghai Jiao Tong Univ, Sch Elect Informat & Elect Engn, Shanghai, Peoples R China.;Xue, H (通讯作者),Singapore Management Univ, Singapore, Singapore.

2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023; (): 14256

Abstract

Typical layout-to-image synthesis (LIS) models generate images for a closed set of semantic classes, e.g., 182 common objects in COCO-Stuff. In this w......

Full Text Link