Learning to See in the Dark

CVPR 2018  ·  Chen Chen, Qifeng Chen, Jia Xu, Vladlen Koltun ·

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

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Datasets


Introduced in the Paper:

SID

Used in the Paper:

11k Hands ELD

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Image Denoising ELD SonyA7S2 x100 SID (paired real data) PSNR (Raw) 44.50 # 2
SSIM 0.971 # 2
Image Denoising ELD SonyA7S2 x200 SID (paired real data) PSNR (Raw) 42.45 # 2
SSIM 0.945 # 2
Image Denoising SID x100 SID (paired real data) PSNR (Raw) 42.06 # 1
SSIM 39.60 # 1
Image Denoising SID x300 SID (paired real data) PSNR (Raw) 36.85 # 1
SSIM 0.923 # 1

Methods


No methods listed for this paper. Add relevant methods here