Noise2Noise: Learning Image Restoration without Clean Data · HackerPapers discussions

Noise2Noise: Learning Image Restoration without Clean Data — HN submission

Sat, 23 Mar 2019 08:23:56 GMT

Nvidia develops AI that can noise, grain and watermarks from photos

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Noise2Noise: Learning Image Restoration without Clean Data — mentioned by dharma1

Fri, 01 Feb 2019 12:33:29 GMT

This is trained on monte carlo based rendering noise, and optionally uses additional available rendering data like albedo and normal passes. So while the idea of using deep learning for noise reduction in general works, this codebase in particular isn't suitable for that task. One issue is also building large enough training data set for clean vs noisy images. Approaches like https://arxiv.org/abs/1803.04189 try to work around that Other approaches (like Google's pixel cameras and astrophotography) additionally take high speed burst photos and average pixels to reduce noise, this can be used…

Paper and discussion history. A mention is not an endorsement.

Noise2Noise: Learning Image Restoration without Clean Data — HN submission

Fri, 05 Oct 2018 10:18:58 GMT

Noise2Noise: Learning Image Restoration Without Clean Data

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Noise2Noise: Learning Image Restoration without Clean Data — HN submission

Wed, 11 Jul 2018 03:34:37 GMT

Noise2Noise: Learning Image Restoration Without Clean Data

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Noise2Noise: Learning Image Restoration without Clean Data — mentioned by webmaven

Tue, 10 Jul 2018 13:18:39 GMT

Noise2Noise paper: https://arxiv.org/pdf/1803.04189.pdf

Paper and discussion history. A mention is not an endorsement.