Learning to See in the Dark

Abstract

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

arXiv commentPublished at the Conference on Computer Vision and Pattern Recognition (CVPR 2018)

References in corpus (6)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• RENOIR - A Dataset for Real Low-Light Image Noise Reduction
• Learning the image processing pipeline
• Fast Image Processing with Fully-Convolutional Networks
• Deep Convolutional Denoising of Low-Light Images

Cited by in corpus (14)

• DeepISP: Towards Learning an End-to-End Image Processing Pipeline
• DeepFlash: Turning a Flash Selfie into a Studio Portrait
• Self-supervised Low Light Image Enhancement and Denoising
• U-NetPlus: A Modified Encoder-Decoder U-Net Architecture for Semantic and Instance Segmentation of Surgical Instrument
• Learning Digital Camera Pipeline for Extreme Low-Light Imaging
• Towards Fast and Light-Weight Restoration of Dark Images
• Deep Learning Techniques for Inverse Problems in Imaging
• End-to-End Denoising of Dark Burst Images Using Recurrent Fully Convolutional Networks
• NODE: Extreme Low Light Raw Image Denoising using a Noise Decomposition Network
• CodedStereo: Learned Phase Masks for Large Depth-of-field Stereo
• Seeing in the dark with recurrent convolutional neural networks
• Very Power Efficient Neural Time-of-Flight
• An Integrated Enhancement Solution for 24-hour Colorful Imaging
• Light Field Neural Network