CVPR 2018: Learning to See in the Dark

Channel:Chen Chen · Length:3:31 · Published:2018-04-24 · Views:190465

Watch on YouTube

Summary

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.

Why HN recommends it

HN commenters flag it as a remarkable machine-learning result, notably for showing that training on raw images beats JPEG.

Remarkable machine learning result for "producing astoundingly sharp photos in very low light — HN, 2018

Machine learning & deep learning · Computer vision, speech & NLP

On Hacker News

Remarkable machine learning result for "producing astoundingly sharp photos in very low light" (Cory Doctorow - [LINK] ) Demo example (one of many examples - drag the middle slider from left-to-right): [LINK] GitHub: [LINK] Paper: [LINK] Video: [VIDEO] — isp, 2018-05
To me the results seem vastly superior to those sort of simple DSP algorithms. The video shows a comparison with some denoising: [VIDEO] — pera, 2020-04
Public raw image datasets are rare, probably because most cameras, except DSLRs, don't support storing raw images. Also, the nature of the inference may not require high fidelity raw images since they're going to be down-sampled anyway. Unless research suggests that raw images improve inference metrics, nobody's going to invest effort into building a raw image dataset. One notable recent exceptio… — lovelearning, 2018-08

Related videos