Low-illumination image enhancement method for spatial adaptive supervised learning

• Main Authors: SHI MINGZHU, KASUHIN, SU YUHAO, LIN XINHUI, TAN MUXIAN, KONG SIQI
• Format: Patent
• Language: Chinese; English
• Published: 01.12.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention discloses a low-illumination image enhancement method for spatial adaptive supervised learning. The method comprises the following steps: inputting a target image into a trained low-illumination enhancement network model for low-illumination enhancement; the low illumination enhancement network model comprises a local branch, a global branch and an adaptive feature fusion module; the local branch obtains local features of the target image; the global branch acquires global features of the target image; and the adaptive feature fusion module fuses the obtained local features and global features to complete low-illumination image enhancement. 本发明公开了一种空间自适应监督学习的低光照图像增强方法，将目标图像输入训练好的低光照增强网络模型中进行低光照增强；所述低光照增强网络模型包括局部分支、全局分支和自适应特征融合模块；所述局部分支获取目标图像的局部特征；所述全局分支获取目标图像的全局特征；所述自适应特征融合模块将所得局部特征和全局特征进行融合，完成低光照图像增强。