Learning to See in the Dark: Neural Networks for Low-Light Images
Chen Chen · Demo · 4 min · 2018 · YouTube title: CVPR 2018: Learning to See in the Dark
Why it's here
HN commenters flag it as a remarkable machine-learning result, notably for showing that training on raw images beats JPEG.
What it covers
A short video accompanying the CVPR 2018 paper Learning to See in the Dark. It shows a neural network producing sharp images from very low-light raw sensor data, compared against denoising approaches.