去模糊
管道(软件)
计算机科学
人工智能
计算机视觉
噪音(视频)
降噪
深度学习
图像处理
管道运输
原始数据
图像(数学)
图像复原
环境科学
环境工程
程序设计语言
作者
Chen Chen,Qifeng Chen,Jing Xu,Vladlen Koltun
出处
期刊:Cornell University - arXiv
日期:2018-05-04
被引量:2
标识
DOI:10.48550/arxiv.1805.01934
摘要
Imaging in low light is challenging due to low photon count and low SNR. Short-exposure images suffer from noise, while long exposure can induce blur and is often impractical. A variety of denoising, deblurring, and enhancement techniques have been proposed, but their effectiveness is limited in extreme conditions, such as video-rate imaging at night. To support the development of learning-based pipelines for low-light image processing, we introduce a dataset of raw short-exposure low-light images, with corresponding long-exposure reference images. Using the presented dataset, we develop a pipeline for processing low-light images, based on end-to-end training of a fully-convolutional network. The network operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data. We report promising results on the new dataset, analyze factors that affect performance, and highlight opportunities for future work. The results are shown in the supplementary video at https://youtu.be/qWKUFK7MWvg
科研通智能强力驱动
Strongly Powered by AbleSci AI