A lightweight multi‐branch network for low‐light image enhancement

The generation process of low-light images is fundamentally complicated due to their multi-factorial degradation. Many previous methods favorably developed a multi-branch network for impressive performance. However, the complex structures networks always incur large computational cost and hinders applicability in those resource-limited settings. To alleviate these issues, this letter novel lightweight (LMBN) image enhancement proposed. Specifically, module joint loss are framed surmount degradation factors images. Furthermore, implemented by several heterogeneous shallow encoder-decoder modules. elaborately designed model facilitates lower complexity but maintains quality. experimental results performed on three popularly benchmark databases demonstrate that proposed LMBN shows superior performance over other state-of-the-art methods, indicating perfect balance between model's efficiency.