Papers of the day   All papers

Analyzing and Improving the Image Quality of StyleGAN


Dec 12 2019 Xander Steenbrugge

Whoa, StyleGANv2 is out! - Significantly better samples (better FID scores & reduced artifacts) - No more progressive growing - Improved Style-mixing - Smoother interpolations (extra regularization) - Faster training Paper: Github:
6 replies, 611 likes

Dec 12 2019 roadrunner01

Analyzing and Improving the Image Quality of StyleGAN pdf: abs: github:
5 replies, 295 likes

Dec 12 2019 Ming-Yu Liu

StyleGAN2 is out.
1 replies, 213 likes

Dec 12 2019 Alexia Jolicoeur-Martineau

NVIDIA basically fixed most of the issues with their architecture. They now use gradient penalty only 1/16 of the times making it much faster and they replaced progressive growing by a modified MSG-GAN (@AnimeshKarnewar). The amount of work done is insane for one single paper.
3 replies, 173 likes

Dec 12 2019 Jonathan Fly ๐Ÿ‘พ

StyleGAN 2: Mostly We Got Rid of The Blobs Also: No 'phase artifacts' (I hadn't noticed them but obvious in retrospect), easier-to-navigate latent spaces mean better encoding, and ~25% more efficient. pdf: code (coming-later):
2 replies, 137 likes

Dec 14 2019 Mikael H Christensen

#StyleGAN2 is out and looking great! I have created a Google Colab notebook to make it easier to get started:
2 replies, 130 likes

Dec 20 2019 Ben Nimmo

Perhaps counter-intuitively, backgrounds are even harder, because there's more variation in scenery than there is in faces.
2 replies, 82 likes

Dec 12 2019 Jaakko Lehtinen

#StyleGAN2 out now
1 replies, 57 likes

Dec 12 2019 ๅฐ็Œซ้Šใ‚Šใ‚‡ใ†๏ผˆใŸใ‹ใซใ‚ƒใ—ใƒปใ‚Šใ‚‡ใ†๏ผ‰

่ซ–ๆ–‡ Analyzing and Improving the Image Quality of StyleGAN StyleGAN2 โ€” Official TensorFlow Implementation
1 replies, 43 likes

Dec 12 2019 Drew Harwell

These are all computer-generated faces. (From new Nvidia AI research:
1 replies, 37 likes

Dec 12 2019 Miles Brundage

Interesting: "It turns out that our improvements to StyleGAN make it easier to detect generated images using projection-based methods, even though the quality of generated images is higher."
1 replies, 35 likes

Dec 12 2019 Jane Lytvynenko ๐Ÿคฆ๐Ÿฝโ€โ™€๏ธ๐Ÿคฆ๐Ÿฝโ€โ™€๏ธ๐Ÿคฆ๐Ÿฝโ€โ™€๏ธ

this tech has gotten so much better in such a short span of time ๐Ÿ˜ฌ
5 replies, 32 likes

Dec 20 2019 Giorgio Patrini ๐Ÿ›ก๏ธ๐Ÿ‘พ

This analysis is excellent @benimmo but please careful: some of these telltales are already solved by StyleGAN v2, and won't be there at the next disinfo automated campaign exploiting synthetic photos
1 replies, 21 likes

Dec 12 2019 Kyle McDonald

NVIDIA just released the latest tech for image generation. I can still find a few artifacts if i zoom in at 1024x1024, but i would guess weโ€™ve passed human recognition at 512x512
2 replies, 19 likes

Dec 12 2019 Koichi Hamada

StyleGAN2: "Analyzing and Improving the Image Quality of StyleGAN" - Github: - ArXiv: - Video:
0 replies, 9 likes

Dec 15 2019 Jeremy Cowles

Update to StyleGAN focused on analyzing the previous architecture, I'm super curious to see what they found:
1 replies, 8 likes

Dec 12 2019 Emmett Macfarlane

0 replies, 7 likes

Dec 12 2019 Shanthi Kalathil

With even just a tiny bit of imagination, it becomes clear that current efforts to develop widespread digital literacy and strengthen democratic resilience are likely to be quickly outpaced.
0 replies, 6 likes

Dec 12 2019 Andy Baio

More info in this thread if you want to learn more.
1 replies, 5 likes

Dec 25 2019 Daisuke Okanohara

StyleGAN2:1) Replace Instance Norm with Weight Norm to remove droplet artifact 2) Introduce path length regularization to minimize perceptual path length 3) skip-connected generator, residual discriminator, no progressive growing.
0 replies, 5 likes

Dec 12 2019 Aaron Gokaslan

StyleGAN v2 is out!
0 replies, 3 likes

Dec 12 2019 Roelof Pieters

StyleGan is back with a V2 overhaul! - Much better quality and FID scores - Removing artefacts by demodulation - No progressive growing - New MSG-GAN architecture - Quicker training Paper: Code:
0 replies, 2 likes

Dec 12 2019 Mรกlaga Artificial Intelligence

StyleGANv2. The authors did a big homework and fixed "light spots" and "burnt skin" artifacts. Also, they proposed an improved method for finding real images in latent space (but still via backprop). ๐Ÿ”Ž ๐Ÿ“ ๐Ÿ“‰ @loss_function_porn
0 replies, 2 likes

Dec 12 2019 Parand Darugar

StyleGAN, the system that creates those eerily realistic portraits you saw at , has been updated to be even more effective: Video: Paper: So many cool things coming out of NeurIPS, wish I was there.
0 replies, 1 likes

Dec 12 2019 Ruqiya

ุชุญุณูŠู† ู„ู„ styleGAN ูˆุฑู‚ุฉ ู†ุดุฑุช ุจู‡ุฐุง ุงู„ุดู‡ุฑ 3 ุฏูŠุณู…ุจุฑ 2019 ุนู†ูˆุงู†ู‡ุง Analyzing and Improving the Image Quality of StyleGAN ุนู„ู‰ ุงู„ุฑุงุจุท ุญุงู„ูŠุง ู…ู‡ุชู…ุฉ ุจุงู„ GANs
0 replies, 1 likes

Dec 21 2019 Deeptrace

@GlennF @razhael Yet it is important to point out that those signs may soon disappear. Version 2 of the StyleGAN model was open sourced just days ago, and claimed to have solved some of the known issues in generation.
1 replies, 0 likes