Real-Scene Image Dehazing via Laplacian Pyramid-Based Conditional Diffusion Model

Yongzhen Wang, Jie Sun, Heng Liu, Xiao–Ping Zhang, Mingqiang WeiIEEE Trans. Multimedia 2025 · DOI

Abstract

Recent diffusion models have demonstrated exceptional efficacy across various image restoration tasks, but still suffer from time-consuming and substantial computational resource consumption. To address these challenges, we present LPCDiff, a novel Laplacian Pyramid-based Conditional Diffusion model designed for real-scene image dehazing. LPCDiff leverages the Laplacian pyramid decomposition to decouple the input image into two components: the low-resolution low-pass image and the high-frequency residuals. These components are subsequently reconstructed through a diffusion model and a well-designed high-frequency residual recovery module. With such a strategy, LPCDiff can substantially accelerate inference speed and reduce computational costs without sacrificing image fidelity. In addition, the framework empowers the model to capture intrinsic high-frequency details and low-frequency structural information within the image, resulting in sharper and more realistic haze-free outputs. Moreover, to extract more valuable information from the limited training data, we introduce a low-frequency refinement module to further enhance the intricate details of the final dehazed images. Through extensive experimentation, our method significantly outperforms 12 state-of-the-art approaches on three real-world and one synthetic image dehazing benchmarks. Code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/yz-wang/LPCDiff</uri>.
BibTeX
@article{wang2025real,
  author = {Yongzhen Wang and Jie Sun and Heng Liu and Xiao–Ping Zhang and Mingqiang Wei},
  title = {{Real-Scene Image Dehazing via Laplacian Pyramid-Based Conditional Diffusion Model}},
  journal = {IEEE Transactions on Multimedia},
  year = {2025},
  doi = {10.1109/tmm.2025.3632694},
}

Loading related content...

Figure