Situation-adaptive neural network for fast pre-computing image enhancement  

作　　者：Xinyue LI Huiyu DUAN Jia WANG Xiaohong LIU Yitong CHEN Guangtao ZHAI 

机构地区：[1]Institute of Image Communication and Network Engineering,Department of Electronic Engineering,Shanghai Jiao Tong University,Shanghai 200240,China

出　　处：《Science China(Information Sciences)》2025年第2期376-378,共3页中国科学(信息科学)(英文版)

基　　金：supported in part by National Natural Science Foundation of China(Grant No.62301310);Shanghai Pujiang Program(Grant No.22PJ1406800)。

摘　　要：As intelligent vision tasks become more widespread,enhancing image quality before further computational analysis is crucial.Recently,deep learning has shown potential for automated pre-computing enhancement,but it typically requires substantial computational resources and is hard to adapt to in multiple situations without re-training.In practice,image enhancement often demands flexible adjustments based on different situations and subsequent computation devices,such as optical computing.

关 键 词：COMPUTING NEURAL IMAGE 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]