Work

Diversifying Similar Subjects for Text-to-Image Synthesis with Self-Cross Diffusion Guidance and Reward

Year: 2026

Type: article

Source: International Journal of Computer Vision

DOI: 10.1007/s11263-026-02947-4

Authors: Weimin Qiu, Jieke Wang, Zhining Gu, Vincent Tao Hu, Meng Tang

Institutions: University of California, Merced, Arizona State University, Ludwig-Maximilians-Universität München

Language: English

Topic: Generative Adversarial Networks and Image Synthesis

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

Funders: U.S. Department of Defense, Google

Award: NEW START GRANT - LEARNING TO SEE BY LEARNING TO SYNTHESIZE IMAGES

OpenAlex ID: W7170136664

FWCI:

Cites: 38

Cited by:

Related to: 10