ZeroIDIR：基于扰动一致性扩散模型的零参考光照退化图像复原
ZeroIDIR: Zero-Reference Illumination Degradation Image Restoration with Perturbed Consistency Diffusion Models
提出零参考扩散框架，将复原解耦为自适应光照校正与扩散重建，并引入扰动一致性损失，为无监督低光照增强与去噪提供可复用方案。
原文依据 we propose a zero-reference diffusion-based framework, named ZeroIDIR, for illumination degradation image restoration
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出了一种名为 ZeroIDIR 的零参考扩散框架，用于光照退化图像复原，该框架将复原过程解耦为自适应光照校正和基于扩散的重建，且仅使用低质量退化图像进行训练。具体而言，我们设计了一个自适应伽马校正模块，执行空间变化的曝光校正以生成仅光照校正的表示，从而缓解曝光偏差并为后续扩散过程提供可靠输入，其中引入了直方图引导的光照校正损失，以将校正后的光照分布正则化至自然场景的分布。随后，将光照校正后的图像视为所提出的扰动一致性扩散模型的中间噪声状态，以重建细节并抑制噪声。此外，提出了一种扰动扩散一致性损失，约束最终复原图像的前向扩散轨迹与扰动状态保持一致，从而在缺乏监督的情况下提高复原保真度和稳定性。在公开基准上的大量实验表明，所提方法优于最优的无监督竞争方法，并与监督方法相当，同时对各种场景具有更好的泛化能力。代码见 https://github.com/JianghaiSCU/ZeroIDIR。
英文原文摘要 1458 字符
In this paper, we propose a zero-reference diffusion-based framework, named ZeroIDIR, for illumination degradation image restoration, which decouples the restoration process into adaptive illumination correction and diffusion-based reconstruction while being trained solely on low-quality degraded images. Specifically, we design an adaptive gamma correction module that performs spatially varying exposure correction to generate illumination-corrected only representations to mitigate exposure bias and serve as reliable inputs for subsequent diffusion processes, where a histogram-guided illumination correction loss is introduced to regularize the corrected illumination distribution toward that of natural scenes. Subsequently, the illumination-corrected image is treated as an intermediate noisy state for the proposed perturbed consistency diffusion model to reconstruct details and suppress noise. Moreover, a perturbed diffusion consistency loss is proposed to constrain the forward diffusion trajectory of the final restored image to remain consistent with the perturbed state, thus improving restoration fidelity and stability in the absence of supervision. Extensive experiments on publicly available benchmarks show that the proposed method outperforms state-of-the-art unsupervised competitors and is comparable to supervised methods while being more generalizable to various scenes. Code is available at https://github.com/JianghaiSCU/ZeroIDIR.