Chen Zeyuan, Jiang Yifan, Liu Dong, Wang Zhangyang
IEEE Trans Image Process. 2022 Jun 14;PP. doi: 10.1109/TIP.2022.3180213.
Low-light images captured in the real world are inevitably corrupted by sensor noise. Such noise is spatially variant and highly dependent on the underlying pixel intensity, deviating from the oversimplified assumptions in conventional denoising. Existing light enhancement methods either overlook the important impact of real-world noise during enhancement, or treat noise removal as a separate pre- or post-processing step. We present Coordinated Enhancement for Real-world Low-light Noisy Images (CERL), that seamlessly integrates light enhancement and noise suppression parts into a unified and physics-grounded optimization framework. For the real low-light noise removal part, we customize a self-supervised denoising model that can easily be adapted without referring to clean ground-truth images. For the light enhancement part, we also improve the design of a state-of-the-art backbone. The two parts are then joint formulated into one principled plug-and-play optimization. Our approach is compared against state-of-the-art low-light enhancement methods both qualitatively and quantitatively. Besides standard benchmarks, we further collect and test on a new realistic low-light mobile photography dataset (RLMP), whose mobile-captured photos display heavier realistic noise than those taken by high-quality cameras. CERL consistently produces the most visually pleasing and artifact-free results across all experiments. Our RLMP dataset and codes are available at: https://github.com/VITA-Group/CERL.
在现实世界中拍摄的低光照图像不可避免地会受到传感器噪声的影响。这种噪声在空间上是变化的，并且高度依赖于底层像素强度，这与传统去噪中过于简化的假设不同。现有的光照增强方法要么在增强过程中忽略了现实世界噪声的重要影响，要么将噪声去除视为一个单独的预处理或后处理步骤。我们提出了用于现实世界低光照噪声图像的协同增强（CERL）方法，该方法将光照增强和噪声抑制部分无缝集成到一个统一的、基于物理的优化框架中。对于实际的低光照噪声去除部分，我们定制了一个自监督去噪模型，该模型无需参考干净的真实图像即可轻松调整。对于光照增强部分，我们还改进了一个先进主干网络的设计。然后将这两个部分联合制定为一个有原则的即插即用优化方法。我们的方法在定性和定量方面都与最先进的低光照增强方法进行了比较。除了标准基准测试外，我们还进一步收集并在一个新的现实低光照手机摄影数据集（RLMP）上进行测试，该数据集的手机拍摄照片比高质量相机拍摄的照片显示出更严重的现实噪声。在所有实验中，CERL始终产生视觉上最令人愉悦且无伪影的结果。我们的RLMP数据集和代码可在以下网址获取：https://github.com/VITA-Group/CERL。
