When Schrödinger Bridge Meets Real-World Image Dehazing with Unpaired Training

• URL: http://arxiv.org/abs/2507.09524v1
• Date: Sun, 13 Jul 2025 07:39:44 GMT
• Title: When Schrödinger Bridge Meets Real-World Image Dehazing with Unpaired Training
• Authors: Yunwei Lan, Zhigao Cui, Xin Luo, Chang Liu, Nian Wang, Menglin Zhang, Yanzhao Su, Dong Liu,
• Abstract summary: We propose DehazeSB, a novel unpaired dehazing framework based on the Schr"odinger Bridge.<n>By leveraging optimal transport (OT) theory, DehazeSB directly bridges the distributions between hazy and clear images.<n>We introduce detail-preserving regularization, which enforces pixel-level alignment between hazy inputs and dehazed outputs.
• Score: 11.606495142345477
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advancements in unpaired dehazing, particularly those using GANs, show promising performance in processing real-world hazy images. However, these methods tend to face limitations due to the generator's limited transport mapping capability, which hinders the full exploitation of their effectiveness in unpaired training paradigms. To address these challenges, we propose DehazeSB, a novel unpaired dehazing framework based on the Schr\"odinger Bridge. By leveraging optimal transport (OT) theory, DehazeSB directly bridges the distributions between hazy and clear images. This enables optimal transport mappings from hazy to clear images in fewer steps, thereby generating high-quality results. To ensure the consistency of structural information and details in the restored images, we introduce detail-preserving regularization, which enforces pixel-level alignment between hazy inputs and dehazed outputs. Furthermore, we propose a novel prompt learning to leverage pre-trained CLIP models in distinguishing hazy images and clear ones, by learning a haze-aware vision-language alignment. Extensive experiments on multiple real-world datasets demonstrate our method's superiority. Code: https://github.com/ywxjm/DehazeSB.

Related papers

• Learning Unpaired Image Dehazing with Physics-based Rehazy Generation [50.37414006427923]
  Overfitting to synthetic training pairs remains a critical challenge in image dehazing.<n>We propose a novel training strategy for unpaired image dehazing, termed Rehazy, to improve both dehazing performance and training stability.
  arXiv  Detail & Related papers  (2025-06-15T12:12:28Z)
• 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)<n>HazeGen harnesses robust generative diffusion priors of real-world hazy images embedded in a pre-trained text-to-image diffusion model.<n>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)
• Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training [11.902218695900217]
  Unpaired training is one of the most effective paradigms for real scene dehazing by learning from hazy and clear images.<n>Inspired by the strong generative capabilities of diffusion models in producing both hazy and clear images, we exploit diffusion prior for real-world image dehazing.<n>We introduce a new perspective for adequately leveraging the representation ability of diffusion models by removing degradation in image and text modalities.
  arXiv  Detail & Related papers  (2025-03-19T09:13:06Z)
• DRACO-DehazeNet: An Efficient Image Dehazing Network Combining Detail Recovery and a Novel Contrastive Learning Paradigm [3.649619954898362]
  We develop Detail Recovery And Contrastive DehazeNet.<n>It provides efficient and effective dehazing via a dense dilated inverted residual block and an attention-based detail recovery network.<n>A major innovation is its ability to train effectively with limited data, achieved through a novel quadruplet loss-based contrastive dehazing paradigm.
  arXiv  Detail & Related papers  (2024-10-18T16:48:31Z)
• WTCL-Dehaze: Rethinking Real-world Image Dehazing via Wavelet Transform and Contrastive Learning [17.129068060454255]
  Single image dehazing is essential for applications such as autonomous driving and surveillance. We propose an enhanced semi-supervised dehazing network that integrates Contrastive Loss and Discrete Wavelet Transform. Our proposed algorithm achieves superior performance and improved robustness compared to state-of-the-art single image dehazing methods.
  arXiv  Detail & Related papers  (2024-10-07T05:36:11Z)
• HazeCLIP: Towards Language Guided Real-World Image Dehazing [62.4454483961341]
  Existing methods have achieved remarkable performance in image dehazing, particularly on synthetic datasets.<n>This paper introduces HazeCLIP, a language-guided adaptation framework designed to enhance the real-world performance of pre-trained dehazing networks.
  arXiv  Detail & Related papers  (2024-07-18T17:18:25Z)
• UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning [57.40713083410888]
  This paper explores contrastive learning with an adversarial training effort to leverage unpaired real-world hazy and clean images. We propose an effective unsupervised contrastive learning paradigm for image dehazing, dubbed UCL-Dehaze. We conduct comprehensive experiments to evaluate our UCL-Dehaze and demonstrate its superiority over the state-of-the-arts.
  arXiv  Detail & Related papers  (2022-05-04T03:25:13Z)
• Enhancing Low-Light Images in Real World via Cross-Image Disentanglement [58.754943762945864]
  We propose a new low-light image enhancement dataset consisting of misaligned training images with real-world corruptions. Our model achieves state-of-the-art performances on both the newly proposed dataset and other popular low-light datasets.
  arXiv  Detail & Related papers  (2022-01-10T03:12:52Z)
• FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing [48.65974971543703]
  We propose a fully end-to-end Generative Adversarial Networks with Fusion-discriminator (FD-GAN) for image dehazing. Our model can generator more natural and realistic dehazed images with less color distortion and fewer artifacts. Experiments have shown that our method reaches state-of-the-art performance on both public synthetic datasets and real-world images.
  arXiv  Detail & Related papers  (2020-01-20T04:36:11Z)

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.