This paper presents a novel network structure with illumination-aware gamma correction and complete image modelling to solve the low-light image enhancement problem. Low-light environments usually lead to less informative large-scale dark areas, directly learning deep representations from low-light images is insensitive to recovering normal illumination. We propose to integrate the effectiveness of gamma correction with the strong modelling capacities of deep networks, which enables the correction factor gamma to be learned in a coarse to elaborate manner via adaptively perceiving the deviated illumination. Because exponential operation introduces high computational complexity, we propose to use Taylor Series to approximate gamma correction, accelerating the training and inference speed. Dark areas usually occupy large scales in low-light images, common local modelling structures, e.g., CNN, SwinIR, are thus insufficient to recover accurate illumination across whole low-light images. We propose a novel Transformer block to completely simulate the dependencies of all pixels across images via a local-to-global hierarchical attention mechanism, so that dark areas could be inferred by borrowing the information from far informative regions in a highly effective manner. Extensive experiments on several benchmark datasets demonstrate that our approach outperforms state-of-the-art methods.

翻译：本文提出一种融合光照感知伽马校正与完整图像建模的新型网络结构，用于解决低光照图像增强问题。低光照环境通常导致大尺度暗区域信息不足，直接从低光照图像中学习深度表征对恢复正常光照不敏感。我们提出将伽马校正的有效性与深度网络的强建模能力相结合，通过自适应感知偏离光照，以从粗到精的方式学习校正因子伽马。由于指数运算带来高计算复杂度，我们提出采用泰勒级数近似伽马校正，从而加速训练与推理速度。暗区域通常在低光照图像中占据较大尺度，因此常见的局部建模结构（如CNN、SwinIR）难以精确恢复整幅低光照图像的照明。我们提出一种新型Transformer块，通过局部到全局的层级注意力机制完整模拟图像中所有像素的依赖关系，从而借助远处信息区域高效推断暗区域。在多个基准数据集上的广泛实验表明，本方法优于现有最先进技术。