Papers of the day   All papers

Analyzing and Improving the Image Quality of StyleGAN

Comments

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: https://arxiv.org/abs/1912.04958 Github: https://github.com/NVlabs/stylegan2 https://t.co/5Cnlg9j91V

6 replies, 611 likes


roadrunner01: Analyzing and Improving the Image Quality of StyleGAN pdf: https://arxiv.org/pdf/1912.04958.pdf abs: https://arxiv.org/abs/1912.04958 github: https://github.com/NVlabs/stylegan2 https://t.co/QK8ROJl9J5

5 replies, 295 likes


Ming-Yu Liu: StyleGAN2 is out. https://arxiv.org/abs/1912.04958

1 replies, 213 likes


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


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: https://arxiv.org/abs/1912.04958 code (coming-later): https://github.com/NVlabs/stylegan2 https://t.co/nw2ddLq0of

2 replies, 137 likes


Mikael H Christensen: #StyleGAN2 is out and looking great! I have created a Google Colab notebook to make it easier to get started: https://colab.research.google.com/drive/1ShgW6wohEFQtqs_znMna3dzrcVoABKIH https://t.co/Jaaj2zVGhW

2 replies, 130 likes


Ben Nimmo: Perhaps counter-intuitively, backgrounds are even harder, because there's more variation in scenery than there is in faces. https://t.co/mWtwRfjwBt

2 replies, 82 likes


Jaakko Lehtinen: This just in: we have updated the #StyleGAN2 paper with estimates of total GPU time and energy consumption, with a breakdown over the different facets of the research project. See new Appendix F and Table 5. https://arxiv.org/abs/1912.04958

1 replies, 65 likes


Jaakko Lehtinen: #StyleGAN2 out now https://arxiv.org/abs/1912.04958

1 replies, 57 likes


ๅฐ็Œซ้Šใ‚Šใ‚‡ใ†๏ผˆใŸใ‹ใซใ‚ƒใ—ใƒปใ‚Šใ‚‡ใ†๏ผ‰: ่ซ–ๆ–‡ Analyzing and Improving the Image Quality of StyleGAN https://arxiv.org/abs/1912.04958 StyleGAN2 โ€” Official TensorFlow Implementation https://github.com/NVlabs/stylegan2

1 replies, 43 likes


Drew Harwell: These are all computer-generated faces. (From new Nvidia AI research: https://arxiv.org/pdf/1912.04958.pdf.) https://t.co/fm36PeikhB

1 replies, 37 likes


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." https://twitter.com/ak92501/status/1204937687649673218?s=20

1 replies, 35 likes


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


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 https://arxiv.org/abs/1912.04958

1 replies, 21 likes


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 https://arxiv.org/abs/1912.04958 https://t.co/REy87VqamX

2 replies, 19 likes


Koichi Hamada: StyleGAN2: "Analyzing and Improving the Image Quality of StyleGAN" - Github: https://github.com/NVlabs/stylegan2 - ArXiv: http://arxiv.org/abs/1912.04958 - Video: https://www.youtube.com/watch?v=c-NJtV9Jvp0

0 replies, 9 likes


Jeremy Cowles: Update to StyleGAN focused on analyzing the previous architecture, I'm super curious to see what they found: https://arxiv.org/abs/1912.04958

1 replies, 8 likes


Emmett Macfarlane: Whoa... https://twitter.com/drewharwell/status/1205116111693455360

0 replies, 7 likes


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


Andy Baio: More info in this thread if you want to learn more. https://twitter.com/xsteenbrugge/status/1205108677641981952?s=21

1 replies, 5 likes


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. https://arxiv.org/abs/1912.04958 https://www.youtube.com/watch?v=c-NJtV9Jvp0

0 replies, 5 likes


Aaron Gokaslan: StyleGAN v2 is out!

0 replies, 3 likes


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: https://arxiv.org/abs/1912.04958 Code: https://github.com/NVlabs/stylegan2 https://t.co/OCt7ZNFXwr

0 replies, 2 likes


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 http://github.com/NVlabs/stylegan2 ๐Ÿ“ http://arxiv.org/abs/1912.04958 ๐Ÿ“‰ @loss_function_porn https://t.co/jJNpMSSlXj

0 replies, 2 likes


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 https://arxiv.org/abs/1912.04958 ุญุงู„ูŠุง ู…ู‡ุชู…ุฉ ุจุงู„ GANs

0 replies, 1 likes


Parand Darugar: StyleGAN, the system that creates those eerily realistic portraits you saw at https://thispersondoesnotexist.com/ , has been updated to be even more effective: Video: https://www.youtube.com/watch?v=c-NJtV9Jvp0 Paper: https://arxiv.org/abs/1912.04958 So many cool things coming out of NeurIPS, wish I was there.

0 replies, 1 likes


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. https://twitter.com/GiorgioPatrini/status/1208171954278207489?s=20

1 replies, 0 likes


Content

Found on Dec 12 2019 at https://arxiv.org/pdf/1912.04958.pdf

PDF content of a computer science paper: Analyzing and Improving the Image Quality of StyleGAN