You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction

TL;DR

This paper introduces a lightweight transformer model with only 90K parameters that effectively enhances images and corrects exposure under challenging lighting conditions, improving visual quality and downstream vision tasks.

Contribution

The paper presents a novel, highly efficient illumination adaptive transformer that restores normal lighting from various exposure issues with minimal parameters and fast processing.

Findings

Outperforms state-of-the-art methods on low-light enhancement datasets.

Significantly improves object detection and segmentation under poor lighting.

Operates with only ~90k parameters and 0.004s speed.

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 is available at https://github.com/cuiziteng/Illumination-Adaptive-Transformer.