High-quality Image Dehazing with Diffusion Model
Image dehazing is quite challenging in dense-haze scenarios, where quite less original information remains in the hazy image. Though previous methods have made marvelous progress, they still suffer from information loss in content and color in dense-haze scenarios. The recently emerged Denoising Diffusion Probabilistic Model (DDPM) exhibits strong generation ability, showing potential for solving this problem. However, DDPM fails to consider the physics property of dehazing task, limiting its information completion capacity. In this work, we propose DehazeDDPM: A DDPM-based and physics-aware image dehazing framework that applies to complex hazy scenarios. Specifically, DehazeDDPM works in two stages. The former stage physically models the dehazing task with the Atmospheric Scattering Model (ASM), pulling the distribution closer to the clear data and endowing DehazeDDPM with fog-aware ability. The latter stage exploits the strong generation ability of DDPM to compensate for the haze-induced huge information loss, by working in conjunction with the physical modelling. Extensive experiments demonstrate that our method attains state-of-the-art performance on both synthetic and real-world hazy datasets.
Code (1)
Tasks
DenoisingImage DehazingmodelMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing
Existing real-world image dehazing methods primarily attempt to fine-tune pre-trained models or adapt their inference procedures, thus heavily relying on the pre-trained models and associated training data. Moreover, res…
Image DehazingImage GenerationSemantic Diffusion Posterior Sampling for Cardiac Ultrasound Dehazing
Echocardiography plays a central role in cardiac imaging, offering dynamic views of the heart that are essential for diagnosis and monitoring. However, image quality can be significantly degraded by haze arising from mul…
Semantic SegmentationUnleashing the Potential of the Semantic Latent Space in Diffusion Models for Image Dehazing
Diffusion models have recently been investigated as powerful generative solvers for image dehazing, owing to their remarkable capability to model the data distribution. However, the massive computational burden imposed b…
Image DehazingProDehaze: Prompting Diffusion Models Toward Faithful Image Dehazing
Recent approaches using large-scale pretrained diffusion models for image dehazing improve perceptual quality but often suffer from hallucination issues, producing unfaithful dehazed image to the original one. To mitigat…
HallucinationImage DehazingFrequency Compensated Diffusion Model for Real-scene Dehazing
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 d…
Image Dehazingmodel