Object-level semantic alignment for enhancing fidelity in text-to-image generation with diffusion models

Image and Vision Computing 2026

View at publisher

Authors: Wenna Liu, Na Tian, Youjia Shao, Wencang Zhao

DOI: 10.1016/j.imavis.2026.105923

Cited by: 0

References: 17

Fields of Study & Subjects

Generative Adversarial Networks and Image Synthesis Multimodal Machine Learning Applications Advanced Neural Network Applications

References 17