A Style-Based Generator Architecture for Generative Adversarial Networks · HackerPapers discussions

A Style-Based Generator Architecture for Generative Adversarial Networks — mentioned by sillysaurusx

Thu, 21 Oct 2021 06:41:32 GMT

> Take your example about StyleGAN vs BigGan, I assume once it became clear that the latter was superior to the former that likely resulted in changes to existing architectures that then found additional improvements. This change in consensus is what enables that and is a good thing. Well, no. :) But I think the "no" is because of the uniqueness of ML rather than a "no" to your point in general. You might be right about other fields; I don't have experience there. In ML, there an enormous number of techniques. Style mixing was presented as a core feature of StyleGAN…

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

A Style-Based Generator Architecture for Generative Adversarial Networks — mentioned by godelski

Thu, 24 Jun 2021 03:16:13 GMT

To be honest I don't think the StyleGAN papers are benchmark chasing. If you read StyleGAN[0], StyleGAN2[1], StyleGAN2-ADA[2], and this paper there is a clear story. They call out the mistakes in the previous papers and resolve them. The papers themselves even admit to where they fall short. But it is research. Problems don't get solved all at once. But if you pay attention to these 4 papers it is very clear Kerras has a very well defined research focus and direction. He's showing his progress over time, sharing it with the community, and learning from the community as well. This is how…

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

A Style-Based Generator Architecture for Generative Adversarial Networks — mentioned by guessmyname

Wed, 20 Feb 2019 05:35:37 GMT

I fixed the format for you: • https://github.com/NVlabs/stylegan • https://arxiv.org/abs/1812.04948 • https://www.youtube.com/watch?v=kSLJriaOumA • https://www.lyrn.ai/2018/12/26/a-style-based-generator-archi... • https://www.youtube.com/watch?v=1ct_P3IZow0

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

A Style-Based Generator Architecture for Generative Adversarial Networks — mentioned by gwern

Wed, 20 Feb 2019 05:29:15 GMT

https://github.com/NVlabs/stylegan https://arxiv.org/abs/1812.04948 https://www.youtube.com/watch?v=kSLJriaOumA https://www.lyrn.ai/2018/12/26/a-style-based-generator-archi... https://www.youtube.com/watch?v=1ct_P3IZow0

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

A Style-Based Generator Architecture for Generative Adversarial Networks — mentioned by huling0

Sun, 17 Feb 2019 02:43:37 GMT

It is based on https://arxiv.org/pdf/1812.04948.pdf Images can easily be generated on the fly. Inference time is ~100ms.

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

A Style-Based Generator Architecture for Generative Adversarial Networks — mentioned by lucidrains

Wed, 13 Feb 2019 18:16:50 GMT

Thanks for all the upvotes! Since I made this site, people have already started to train on datasets beyond just real faces. Turns out it can disentangle pretty much any set of data. Gwern has applied this to anime dataset https://twitter.com/gwern/status/1095131651246575616 Cyril at Google has applied it to artwork https://twitter.com/kikko_fr/status/1094685986691399681 This was to raise awareness for what a talented group of researchers made at Nvidia over the course of 2 years, the latest state of the art for GANs. https://arxiv.org/pdf/1812.04948.pdf (https://github.com/NVlabs/stylegan)…

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

A Style-Based Generator Architecture for Generative Adversarial Networks — mentioned by wardbradt

Wed, 13 Feb 2019 02:59:45 GMT

Googling "nvidia face generator" lead me to "A Style-Based Generator Architecture for Generative Adversarial Networks," (6 Feb 2019) a paper showing the faces on the site. https://arxiv.org/pdf/1812.04948.pdf

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

A Style-Based Generator Architecture for Generative Adversarial Networks — mentioned by lucidrains

Mon, 11 Feb 2019 18:58:54 GMT

This is just to raise awareness for how powerful the generative models have become with the recently open sourced https://github.com/NVlabs/stylegan Based on work from https://arxiv.org/abs/1812.04948

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

A Style-Based Generator Architecture for Generative Adversarial Networks — mentioned by jmiserez

Wed, 26 Dec 2018 13:34:45 GMT

Original article here: https://www.theverge.com/2018/12/17/18144356/ai-image-genera... Source paper: https://arxiv.org/pdf/1812.04948.pdf

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

A Style-Based Generator Architecture for Generative Adversarial Networks — HN submission

Thu, 13 Dec 2018 19:47:43 GMT

A Style-Based Generator Architecture for Generative Adversarial Networks [pdf]

78 points; 6 discussion replies on HN. Paper and source history. A submission is not an endorsement.