Learning to See in the Dark

Code

• github.com/cydonia999/Learning_to_See_in_the_Dark_PyTorch
  pytorch★ 95
• github.com/mindspore-ai/models/blob/master/research/cv/LearningToSeeInTheDark
  mindspore★ 0
• github.com/danilka-na/DegreeWork
  pytorch★ 0
• github.com/ashikshafi08/learning_to_see_in_the_dark_Fastai
  none★ 0
• github.com/compscikaran/nightlight-web
  tf★ 0
• github.com/someshfengde/learning_to_see_in_dark
  none★ 0
• github.com/code-implementation1/Code4/tree/main/LearningToSeeInTheDark
  mindspore★ 0
• github.com/kauziishere/lowLightImageEnhancement
  tf★ 0
• github.com/nickolor/Learning-to-See-in-the-Dark
  tf★ 0
• github.com/nickolor/Learning-to-See-in-the-Dark_and_DeepISP
  tf★ 0

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

Tasks

Benchmark Results

Reproductions