You Only Need 90K Parameters to Adapt Light: a Light Weight Transformer for Image Enhancement and Exposure Correction
Ziteng Cui (The University of Tokyo), Kunchang Li (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences), Lin Gu (RIKEN，AIP / The University of Tokyo),* Shenghan Su (Shanghai Jiao Tong University), Peng Gao (Chinese university of hong kong), ZhengKai Jiang (Tencent Youtu Lab), Yu Qiao (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences), Tatsuya Harada (The University of Tokyo / RIKEN)
The 33rd British Machine Vision Conference
Abstract
Challenging illumination conditions (low light, under-exposure and over-exposure) in the real world not only cast an unpleasant visual appearance but also taint the computer vision tasks. After camera captures the raw-RGB data, it renders standard sRGB images with image signal processor (ISP). By decomposing ISP pipeline into local and global image components, we propose a lightweight fast Illumination Adaptive Transformer (IAT) to restore the normal lit sRGB image from either low-light or under/over-exposure conditions. Specifically, IAT uses attention queries to represent and adjust the ISP-related parameters such as colour correction, gamma correction. With only ~90k parameters and ~0.004s processing speed, our IAT consistently achieves superior performance over SOTA on the current benchmark low-light enhancement and exposure correction datasets. Competitive experimental performance also demonstrates that our IAT significantly enhances object detection and semantic segmentation tasks under various light conditions. Training code and pretrained model will be released upon publication.Video
Citation
@inproceedings{Cui_2022_BMVC,
author = {Ziteng Cui and Kunchang Li and Lin Gu and Shenghan Su and Peng Gao and ZhengKai Jiang and Yu Qiao and Tatsuya Harada},
title = {You Only Need 90K Parameters to Adapt Light: a Light Weight Transformer for Image Enhancement and Exposure Correction},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0238.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by