Physics-Guided Image Dehazing Diffusion

• URL: http://arxiv.org/abs/2504.21385v2
• Date: Fri, 15 Aug 2025 02:18:03 GMT
• Title: Physics-Guided Image Dehazing Diffusion
• Authors: Shijun Zhou, Baojie Fan, Jiandong Tian,
• Abstract summary: Current data-driven dehazing algorithms trained on synthetic datasets perform well on synthetic data but struggle to generalize to real-world scenarios.<n>We propose textbfImage textbfDehazing textbfDiffusion textbfModels (IDDM), a novel diffusion process that incorporates the atmospheric scattering model into noise diffusion.
• Score: 35.93081248202844
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Due to the domain gap between real-world and synthetic hazy images, current data-driven dehazing algorithms trained on synthetic datasets perform well on synthetic data but struggle to generalize to real-world scenarios. To address this challenge, we propose \textbf{I}mage \textbf{D}ehazing \textbf{D}iffusion \textbf{M}odels (IDDM), a novel diffusion process that incorporates the atmospheric scattering model into noise diffusion. IDDM aims to use the gradual haze formation process to help the denoising Unet robustly learn the distribution of clear images from the conditional input hazy images. We design a specialized training strategy centered around IDDM. Diffusion models are leveraged to bridge the domain gap from synthetic to real-world, while the atmospheric scattering model provides physical guidance for haze formation. During the forward process, IDDM simultaneously introduces haze and noise into clear images, and then robustly separates them during the sampling process. By training with physics-guided information, IDDM shows the ability of domain generalization, and effectively restores the real-world hazy images despite being trained on synthetic datasets. Extensive experiments demonstrate the effectiveness of our method through both quantitative and qualitative comparisons with state-of-the-art approaches.

Related papers

• Detecting AI-Generated Images via Diffusion Snap-Back Reconstruction: A Forensic Approach [0.0]
  Traditional deepfake detection methods fail against text-to-image systems such as Stable Diffusion and DALL-E.<n>This paper introduces a diffusion-based forensic framework that leverages multi-strength image reconstruction dynamics.
  arXiv  Detail & Related papers  (2025-11-01T01:35:54Z)
• Residual-based Efficient Bidirectional Diffusion Model for Image Dehazing and Haze Generation [17.043633726365233]
  Current deep dehazing methods only focus on removing haze from hazy images, lacking the capability to translate between hazy and haze-free images.<n>We propose a residual-based efficient bidirectional diffusion model (RBDM) that can model the conditional distributions for both dehazing and haze generation.<n>Our RBDM successfully implements size-agnostic bidirectional transitions between haze-free and hazy images with only 15 sampling steps.
  arXiv  Detail & Related papers  (2025-08-15T01:00:15Z)
• BokehDiff: Neural Lens Blur with One-Step Diffusion [62.59018200914645]
  We introduce BokehDiff, a lens blur rendering method that achieves physically accurate and visually appealing outcomes.<n>Our method employs a physics-inspired self-attention module that aligns with the image formation process.<n>We adapt the diffusion model to the one-step inference scheme without introducing additional noise, and achieve results of high quality and fidelity.
  arXiv  Detail & Related papers  (2025-07-24T03:23:19Z)
• Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing [92.61216319417208]
  We propose a novel frequency domain-based diffusion model, named ours, for fully exploiting the beneficial knowledge in unpaired clear data.<n>Inspired by the strong generative ability shown by Diffusion Models (DMs), we tackle the dehazing task from the perspective of frequency domain reconstruction.
  arXiv  Detail & Related papers  (2025-07-02T01:22:46Z)
• When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class [18.81528537866941]
  Open-source pre-trained models hold great potential for diverse applications, but their utility declines when their training data is unavailable.<n>Data-Free Image Synthesis (DFIS) aims to generate images that approximate the learned data distribution of a pre-trained model without accessing the original data.<n>DDIS is the first Diffusion-assisted Data-free Image Synthesis method that leverages a text-to-image diffusion model as a powerful image prior.
  arXiv  Detail & Related papers  (2025-06-18T11:51:40Z)
• Deep Diffusion Models and Unsupervised Hyperspectral Unmixing for Realistic Abundance Map Synthesis [0.2812395851874055]
  Our framework integrates blind linear hyperspectral unmixing with state-of-the-art diffusion models to enhance the realism and diversity of synthetic abundance maps.<n>We validate our approach using real hyperspectral imagery from the PRISMA space mission for Earth observation.
  arXiv  Detail & Related papers  (2025-06-16T13:42:51Z)
• Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing [59.43187521828543]
  We introduce a novel hazing-dehazing pipeline consisting of a Realistic Hazy Image Generation framework (HazeGen) and a Diffusion-based Dehazing framework (DiffDehaze) HazeGen harnesses robust generative diffusion priors of real-world hazy images embedded in a pre-trained text-to-image diffusion model. By employing specialized hybrid training and blended sampling strategies, HazeGen produces realistic and diverse hazy images as high-quality training data for DiffDehaze.
  arXiv  Detail & Related papers  (2025-03-25T01:55:39Z)
• SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation [29.49217721233131]
  diffusion generative models simulate a random walk in the data space along the denoising trajectory.<n>This allows information to diffuse across regions, yielding outcomes.<n>However, the chaotic and disordered nature of information diffusion in diffusion models often results in undesired interference between image regions, causing degraded detail preservation and contextual inconsistency.<n>We reframing disordered diffusion as a powerful tool for text-vision-to-image generation (TV2I) tasks, achieving pixel-level condition fidelity while maintaining visual and semantic coherence throughout the image.
  arXiv  Detail & Related papers  (2024-11-28T14:35:25Z)
• Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior [63.64088590653005]
  We propose Diff-Mosaic, a data augmentation method based on the diffusion model. We introduce an enhancement network called Pixel-Prior, which generates highly coordinated and realistic Mosaic images. In the second stage, we propose an image enhancement strategy named Diff-Prior. This strategy utilizes diffusion priors to model images in the real-world scene.
  arXiv  Detail & Related papers  (2024-06-02T06:23:05Z)
• Teacher-Student Network for Real-World Face Super-Resolution with Progressive Embedding of Edge Information [2.280954956645056]
  A real-world face super-resolution teacher-student model is proposed, which considers the domain gap between real and synthetic data. Our proposed approach surpasses state-of-the-art methods in obtaining high-quality face images for real-world FSR.
  arXiv  Detail & Related papers  (2024-05-08T02:48:52Z)
• Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Medical Image Reconstruction [75.91471250967703]
  We introduce a novel sampling framework called Steerable Conditional Diffusion.<n>This framework adapts the diffusion model, concurrently with image reconstruction, based solely on the information provided by the available measurement.<n>We achieve substantial enhancements in out-of-distribution performance across diverse imaging modalities.
  arXiv  Detail & Related papers  (2023-08-28T08:47:06Z)
• Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
  Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance. We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-22T12:18:20Z)
• Person Image Synthesis via Denoising Diffusion Model [116.34633988927429]
  We show how denoising diffusion models can be applied for high-fidelity person image synthesis. Our results on two large-scale benchmarks and a user study demonstrate the photorealism of our proposed approach under challenging scenarios.
  arXiv  Detail & Related papers  (2022-11-22T18:59:50Z)
• Dual-Scale Single Image Dehazing Via Neural Augmentation [29.019279446792623]
  A novel single image dehazing algorithm is introduced by combining model-based and data-driven approaches. Results indicate that the proposed algorithm can remove haze well from real-world and synthetic hazy images.
  arXiv  Detail & Related papers  (2022-09-13T11:56:03Z)
• High-Resolution Image Synthesis with Latent Diffusion Models [14.786952412297808]
  Training diffusion models on autoencoders allows for the first time to reach a near-optimal point between complexity reduction and detail preservation. Our latent diffusion models (LDMs) achieve a new state of the art for image inpainting and highly competitive performance on various tasks.
  arXiv  Detail & Related papers  (2021-12-20T18:55:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.