Frequency Compensated Diffusion Model for Real-scene Dehazing
Preprint
Abstract
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 dehazing framework based on conditional diffusion models for improved generalization to real haze. First, we find that optimizing the training objective of diffusion models, i.e., Gaussian noise vectors, is non-trivial. The spectral bias of deep networks hinders the higher frequency modes in Gaussian vectors from being learned and hence impairs the reconstruction of image details. To tackle this issue, we design a network unit, named Frequency Compensation block (FCB), with a bank of filters that jointly emphasize the mid-to-high frequencies of an input signal. We demonstrate that diffusion models with FCB achieve significant gains in both perceptual and distortion metrics. Second, to further boost the generalization performance, we propose a novel data synthesis pipeline, HazeAug, to augment haze in terms of degree and diversity. Within the framework, a solid baseline for blind dehazing is set up where models are trained on synthetic hazy-clean pairs, and directly generalize to real data. Extensive evaluations show that the proposed dehazing diffusion model significantly outperforms state-of-the-art methods on real-world images. Our code is at https://github.com/W-Jilly/frequency-compensated-diffusion-model-pytorch.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Self-Guided Image Dehazing Using Progressive Feature FusionIEEE Transactions on Image Processing, 2022
- End-to-End Single Image Fog Removal Using Enhanced Cycle Consistent Adversarial NetworksIEEE Transactions on Image Processing, 2020
- Benchmarking Single-Image Dehazing and BeyondIEEE Transactions on Image Processing, 2018
- Unsupervised Monocular Depth Estimation with Left-Right Consistency2017
- DehazeNet: An End-to-End System for Single Image Haze RemovalIEEE Transactions on Image Processing, 2016
- A Fast Single Image Haze Removal Algorithm Using Color Attenuation PriorIEEE Transactions on Image Processing, 2015
- Visual-PSNR measure of image qualityJournal of Visual Communication and Image Representation, 2014
- Bayesian DefoggingInternational Journal of Computer Vision, 2011
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Image Processing, Analysis and Machine Vision1993