Previous raw image-based low-light image enhancement methods predominantly relied on feed-forward neural networks to learn deterministic mappings from low-light to normally-exposed images. However, they failed to capture critical distribution information, leading to visually undesirable results. This work addresses the issue by seamlessly integrating a diffusion model with a physics-based exposure model. Different from a vanilla diffusion model that has to perform Gaussian denoising, with the injected physics-based exposure model, our restoration process can directly start from a noisy image instead of pure noise. As such, our method obtains significantly improved performance and reduced inference time compared with vanilla diffusion models. To make full use of the advantages of different intermediate steps, we further propose an adaptive residual layer that effectively screens out the side-effect in the iterative refinement when the intermediate results have been already well-exposed. The proposed framework can work with both real-paired datasets, SOTA noise models, and different backbone networks. Note that, the proposed framework is compatible with real-paired datasets, real/synthetic noise models, and different backbone networks. We evaluate the proposed method on various public benchmarks, achieving promising results with consistent improvements using different exposure models and backbones. Besides, the proposed method achieves better generalization capacity for unseen amplifying ratios and better performance than a larger feedforward neural model when few parameters are adopted.

翻译：以往基于原始图像的低光图像增强方法主要依赖前馈神经网络学习从低光图像到正常曝光图像的决定性映射。然而，这些方法未能捕捉关键的分布信息，导致视觉上不理想的结果。本研究通过将扩散模型与基于物理的曝光模型无缝集成来解决该问题。与需执行高斯去噪的标准扩散模型不同，通过引入基于物理的曝光模型，我们的修复过程可直接从噪声图像而非纯噪声开始。因此，与标准扩散模型相比，本方法显著提升了性能并缩短了推理时间。为充分利用不同中间步骤的优势，我们进一步提出自适应残差层，当中间结果已充分曝光时，可有效消除迭代优化中的副作用。该框架可兼容真实配对数据集、最先进噪声模型及不同骨干网络。值得注意的是，所提框架支持真实配对数据集、真实/合成噪声模型及多种骨干网络。我们在多个公开基准上评估了该方法，通过采用不同曝光模型与骨干网络实现了一致的性能提升。此外，本方法在未见放大倍数下展现出更优的泛化能力，且采用较少参数时性能优于更大规模的前馈神经网络模型。