Prior knowledge guided text to image generation

Open Webpage

An-An Liu, Zefang Sun, Ning Xu, Rongbao Kang, Jinbo Cao, Fan Yang, Weijun Qin, Shenyuan Zhang, Jiaqi Zhang, Xuanya Li

Published: 2024, Last Modified: 23 Jan 2026Pattern Recognit. Lett. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•We decompose the image into a superposition of several visual regions.•We provide related prior knowledge as input to enhance the quality of each visual regions.•We help establish the semantic mapping between the knowledge captions and the corresponding image regions.•Extensive experiments on CUB and COCO datasets demonstrate the superior performance of the proposed method.