IEEE

Diff-MEF: Cross-Modal Diffusion Framework With Text Prompts and Semantic Perception for Multi-Exposure Image Fusion

Abstract: The absence of real-world ground truth (GT) remains a challenge in multi-exposure image fusion (MEF). Benchmarks synthesizing pseudo GT through algorithm ensembles. Existing methods, ...
IEEE

DMF-GAN: Deep Multimodal Fusion Generative Adversarial Networks for Text-to-Image Synthesis

Abstract: Text-to-image synthesis aims to generate high-quality realistic images conditioned on text description. The great challenge of this task depends on deeply and seamlessly integrating image ...