Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network · HackerPapers discussions

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network — mentioned by shakna

Mon, 06 Jul 2020 15:29:44 GMT

Upscaling videos. This is a hard problem. It may not even be perfectly solvable at any time in the future. When you increase the size of any kind of raster image, you're creating new information from the old. There's been some pretty good approaches out there, like this [1][2]. It uses a GAN topology for some impressive results, but is incredibly memory intensive and can take a very long time to run. I've been working on something [0] for a good long while which is a less expensive approach. Instead of attempting to replicate everything 1:1, it intentionally allows some detail loss, whilst…

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

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network — HN submission

Sun, 19 Feb 2017 22:16:10 GMT

Photo-Realistic Single Image Super-Resolution Using a Adversarial Network

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

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network — mentioned by ingenter

Mon, 16 Jan 2017 23:01:50 GMT

Here's a list of various image interpolation techniques: - http://www.ifp.illinois.edu/~jyang29/papers/chap1.pdf * Image super-resolution: Historical overview and future challenges - http://www.robots.ox.ac.uk/~vgg/publications/papers/pickup08... * Machine Learning in Multi-frame Image Super-resolution - http://www.cs.huji.ac.il/~peleg/papers/icpr90-SuperResolutio... - http://www.wisdom.weizmann.ac.il/~vision/SingleImageSR.html - http://chiranjivi.tripod.com/EDITut.html - http://www.tecnick.com/pagefiles/appunti/iNEDI_tesi_Nicola_A...…

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

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network — mentioned by nl

Thu, 08 Dec 2016 02:42:04 GMT

Because that isn't true? Looking at the first thing (GANs): developed by Ian Goodfellow, who is now at OpenAI. The first linked paper (https://arxiv.org/pdf/1605.05396v2.pdf) is out of University of Michigan and Max Planck Institute. The second (https://phillipi.github.io/pix2pix/) is out of Berkeley, the third (https://arxiv.org/pdf/1609.04802v3.pdf) is out of Twitter (which I guess counts as a rich American tech company). Google Brain/DeepMind/FAIR/MS Research do great work, but there is plenty of great work elsewhere too. For example, just yesterday an implementation[1] of Fast Layer…

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

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network — mentioned by fhuszar

Mon, 14 Nov 2016 23:24:26 GMT

Some of the deeper - and wider - convolutional neural network-based SR methods do this, implicitly. We have a few papers, like SRGAN (https://arxiv.org/abs/1609.04802) or AffGAN (https://arxiv.org/abs/1610.04490) that generate pretty interesting context-aware textures. Sophisticated hallucination of missing details comes at a cost: As one would expect, in some cases the algorithm guesses incorrectly. See for example Figure 5 of AffGAN paper, column 3: when superresolving an image of a snake, the algorithm mistakenly thought it's a body of water, and produces textures accordingly. Overall we…

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

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network — mentioned by nuclai

Sat, 29 Oct 2016 15:49:47 GMT

(Author here.) My biggest insight from this project is that super-resolution with neural networks benefits significantly from being domain specific. If you train on broader datasets, it does pretty well but has to make compromises. Many recent papers do a comparison in terms of pixel similarity (PSNR/SSIM), and using those metrics the quality drops because high-frequency detail is punished under those criteria (even though it may look better perceptually). Reference: http://arxiv.org/abs/1609.04802 On GitHub, below each GIF there's a demo comparison, but on the site you can also submit your…

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

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network — mentioned by ingenter

Sat, 29 Oct 2016 11:33:22 GMT

Here's a list of various image interpolation techniques, with similar goal: - http://www.wisdom.weizmann.ac.il/~vision/SingleImageSR.html - http://chiranjivi.tripod.com/EDITut.html - http://www.tecnick.com/pagefiles/appunti/iNEDI_tesi_Nicola_A... - http://www.eurasip.org/Proceedings/Eusipco/Eusipco2009/conte... - http://bengal.missouri.edu/~kes25c/ http://bengal.missouri.edu/~kes25c/nnedi3.zip http://forum.doom9.org/showthread.php?t=147695 - http://arxiv.org/pdf/1501.00092v2.pdf http://waifu2x.udp.jp/ https://github.com/nagadomi/waifu2x http://waifu2x-avisynth.sunnyone.org/…

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

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network — mentioned by dharma1

Sat, 29 Oct 2016 07:17:21 GMT

Agreed, it would have been nice to show other upscaling algorithms. But neural net super resolution generators can still have significantly more detail at 4-8x, as shown here http://arxiv.org/abs/1609.04802

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

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network — mentioned by anotheryou

Sun, 02 Oct 2016 12:10:18 GMT

from trustswz' comment: https://arxiv.org/abs/1609.04802 The pic with the boat on page 13 is interesting. In the SRGAN version I would take the shore for some sort of cliff, while the original shows separated boulders.

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

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network — mentioned by trustswz

Sat, 01 Oct 2016 23:21:11 GMT

If you are interested in how it compares to bicubic or the original. Check these papers using the sub pixel convolutional layer: https://arxiv.org/abs/1609.05158 https://arxiv.org/abs/1609.04802.

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

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network — mentioned by dharma1

Sat, 24 Sep 2016 17:46:49 GMT

Yes http://arxiv.org/abs/1609.04802

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

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network — HN submission

Fri, 16 Sep 2016 12:37:15 GMT

Photo-Realistic Single Image Super-Resolution

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