Existing diffusion-based methods have recently made significant progress in image dehazing. However, they typically neglect the physics of haze formation and reconstruct clean images from pure Gaussian noise, thereby limiting their restoration potential. To address this issue, we propose Haze-Noise Diffusion (HNDiff), a novel diffusion framework that embeds the atmospheric scattering model as an inductive bias. By grounding diffusion in physical principles, HNDiff ensures that the restoration aligns more closely with underlying mechanisms of haze formation. In its forward process, we introduce joint haze-noise diffusion with a haze-aware noise scheduler, which progressively adds both haze and noise to an image. Essentially, the scheduler adapts noise levels according to haze density, meaning that regions with heavier haze receive stronger noise injection to encourage content generation, while clearer regions receive lighter noise to better preserve details, which directly links the forward degradation process with the physics of haze. In the reverse process, we then derive a physically consistent dehazing-denoising process that simultaneously removes haze and noise to restore a clean image in a manner aligned with the forward degradation process. To further enhance practicality, we propose Latent HNDiff, which compiles clean latent priors that can be seamlessly integrated into existing dehazing networks to boost performance. Extensive experiments show that our work significantly improves leading dehazing backbones and achieves state-of-the-art results on benchmark datasets. The project page is available at https://jin-ting-he.github.io/HNDiff/.
- HNDiff: Haze-Noise Diffusion for Image Dehazing
- Jin-Ting HeFu-Jen TsaiYan-Tsung PengMin-Hung ChenChia-Wen LinYen-Yu Lin
- Paolo FavaroZuzana KukelovaAtsuto MakiAnna RohrbachKonrad SchindlerFederico Tombari
- Lecture Notes in Computer Science
- Springer Nature Switzerland; Cham
- 19
- Book chapter
- 15/09/2026
- Computer Vision – ECCV 2026, Vol.17016, pp.115-133
- English
- National Science and Technology Council (NSTC): 114-2221-E-A49-038-MY3, 115-2634-F-A49-011, 113-2221-E-004-001-MY3, 114-2221-E-007-065-MY3 NVIDIA Taiwan AI Research & Development Center (TRDC)
This work was supported in part by the National Science and Technology Council (NSTC) under grants 114-2221-E-A49-038-MY3, 115-2634-F-A49-011, 113-2221-E-004-001-MY3, 114-2221-E-007-065-MY3 and by the NVIDIA Taiwan AI Research & Development Center (TRDC). This work was supported by H100 GPU computing resources donated by Wistron.