Learning to See in the Dark
Chen Chen -UIUC, Qifeng Chen - Intel Labs, Jia Xu - Intel Labs, Vladlen Koltun - Intel Labs
Celý článek najdete ve formátu PDF na adrese:
Cituji abstrakt a závěr článku:
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 learningbased 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 fullyconvolutional 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.
We expect future work to yield further improvements in image quality, for example by systematically optimizing the network architecture and training procedure. We hope that the SID dataset and our experimental findings can stimulate and support such systematic investigation.