# ZID-Net: Zero-Inference Diffusion Prior Decoupling Network for Single Image Dehazing

arXiv: https://arxiv.org/abs/2604.23709 · HTML: https://mlsanity.com/paper/2604.23709/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 19 of its 43 references that are in the map.
- First posted on arXiv 26 Apr 2026.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 19 of 19)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [DehazeNet: An End-to-End System for Single Image Haze Removal](https://mlsanity.com/paper/1601.07661/) (2016)
- [FFA-Net: Feature Fusion Attention Network for Single Image Dehazing](https://mlsanity.com/paper/1911.07559/) (2019)
- [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022)
- [DiffIR: Efficient Diffusion Model for Image Restoration](https://mlsanity.com/paper/2303.09472/) (2023)
- [NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images](https://mlsanity.com/paper/2005.03560/) (2020)
- [Dense Haze: A benchmark for image dehazing with dense-haze and haze-free images](https://mlsanity.com/paper/1904.02904/) (2019)
- [O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images](https://mlsanity.com/paper/1804.05101/) (2018)
- [DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention](https://mlsanity.com/paper/2301.04805/) (2023)
- [Curricular Contrastive Regularization for Physics-aware Single Image Dehazing](https://mlsanity.com/paper/2303.14218/) (2023)
- [MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing](https://mlsanity.com/paper/2308.14036/) (2023)
- [I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images](https://mlsanity.com/paper/1804.05091/) (2018)
- [MB-TaylorFormer V2: Improved Multi-branch Linear Transformer Expanded by Taylor Formula for Image Restoration](https://mlsanity.com/paper/2501.04486/) (2025)
- [Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing](https://mlsanity.com/paper/2403.01105/) (2024)
- [Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing](https://mlsanity.com/paper/2503.19262/) (2025)
- [Guided Real Image Dehazing using YCbCr Color Space](https://mlsanity.com/paper/2412.17496/) (2024)
- [All-in-one Weather-degraded Image Restoration via Adaptive Degradation-aware Self-prompting Model](https://mlsanity.com/paper/2411.07445/) (2024)
- [Frequency-Guided Posterior Sampling for Diffusion-Based Image Restoration](https://mlsanity.com/paper/2411.15295/) (2024)
- [UDPNet: Unleashing Depth-based Priors for Robust Image Dehazing](https://mlsanity.com/paper/2601.06909/) (2026)

## Abstract (arXiv)

Single image dehazing is often constrained by a trade-off between restoration quality and computational efficiency. While efficient, CNNs struggle to learn robust priors for dense and non-homogeneous haze. Conversely, diffusion models provide strong generative priors but suffer from severe inference latency and sampling instability. To address these limitations, we propose ZID-Net, a novel framework that explicitly decouples diffusion supervision from feed-forward inference. For efficient inference, we design a frequency-spatial decoupled feed-forward backbone. Within this backbone, a Channel-Spatial Laplacian Mask (CSLM) filters haze-amplified noise to extract purified structural details, while Lightweight Global Context Blocks (LGCBs) establish long-range spatial dependencies to capture global haze variations. A Dynamic Feature Arbitration Block (DFAB) then adaptively fuses these semantic and structural features for robust reconstruction. To provide the backbone with degradation-aware priors without increasing inference cost, we introduce a Zero-Inference Prior Propagation Head (ZI-PPH) during training. ZI-PPH leverages a conditional diffusion process to predict residual noise and regularize the shared representation. By discarding the diffusion branch at test time, ZID-Net integrates the representation-shaping benefits of diffusion supervision into a pure feed-forward architecture. Extensive experiments on synthetic, real-world, and remote-sensing benchmarks demonstrate robust restoration across diverse haze conditions, with particularly strong performance on StateHaze1k, where ZID-Net achieves an average PSNR gain of 3.06 dB while maintaining efficient deterministic inference at 19.35 ms.