论文标题
您只需要90k参数即可调整光：轻巧的变压器用于图像增强和曝光校正
You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction
论文作者
论文摘要
在现实世界中，具有挑战性的照明条件（弱光，暴露不足和过度暴露）不仅具有令人不愉快的视觉外观，而且还会污染计算机视觉任务。在摄像机捕获RAW-RGB数据后，它将使用图像信号处理器（ISP）渲染标准SRGB图像。通过将ISP管道分解为局部和全局图像组件，我们提出了一个轻巧的快速照明自适应变压器（IAT），以从弱光或过度暴露条件下恢复正常的LIT SRGB图像。具体而言，IAT使用注意查询来表示和调整与ISP相关的参数，例如颜色校正，伽马校正。我们的IAT仅〜90K参数和〜0.004S的处理速度，在当前基准低光增强和暴露校正数据集上，IAT始终达到了比SOTA的卓越性能。竞争性实验性能还表明，我们的IAT在各种光条件下显着增强了对象检测和语义分割任务。培训代码和预估计的模型可从https://github.com/cuiziteng/illumination-aptive-transformer获得。
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.
