2 papers
cs.CV2025
ProDehaze: Prompting Diffusion Models Toward Faithful Image Dehazing
Tianwen Zhou, Jing Wang, Songtao Wu +1
Recent approaches using large-scale pretrained diffusion models for image dehazing improve perceptual quality but often suffer from hallucination issues, producing unfaithful dehaz…
cs.CV2023
Frequency Compensated Diffusion Model for Real-scene Dehazing
Jing Wang, Songtao Wu, Kuanhong Xu +1
Due to distribution shift, deep learning based methods for image dehazing suffer from performance degradation when applied to real-world hazy images. In this paper, we consider a d…