Analyzing and Improving the Image Quality of StyleGAN · HackerPapers discussions

Analyzing and Improving the Image Quality of StyleGAN — mentioned by Two_hands

Mon, 28 Oct 2024 07:01:29 GMT

I've been working a lot on my blog, which entails training and implementing neural networks. My next two posts are going to be about: - https://arxiv.org/pdf/1912.04958 - StyleGAN2 - https://arxiv.org/pdf/1807.09341 - Causal InfoGAN, written in TinyGrad https://ym2132.github.io

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

Analyzing and Improving the Image Quality of StyleGAN — mentioned by fxtentacle

Thu, 21 Jul 2022 16:37:05 GMT

> The denoising part of a denoising autoencoder refers to the noise applied to its input Agree, it converts a noisy image to a denoised image. But the odd thing is, when you put a noisy image into a StyleGAN2 encoder, you get latents which the decoder will turn into a de-noised image. So in practical use, you can take a trained StyleGAN2 encoder/decoder pair and use it as if it was a denoiser. For example https://arxiv.org/abs/2103.04192 > These differences lead to learned distributions in the latent space that are entirely different I also agree there. The training for a denoising…

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

Analyzing and Improving the Image Quality of StyleGAN — 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.

Analyzing and Improving the Image Quality of StyleGAN — mentioned by godelski

Wed, 03 Feb 2021 02:24:32 GMT

The StyleGAN2 paper[0] actually addresses some of the biggest clues. They didn't completely solve everything but symmetry is one of the biggest indicators. Specifically ears and eyes. But also really pay attention to the teeth. If you go to ThisPersonDoesNotExist[1] you'll see that there's still phase issues with teeth and eyes. It's an improvement on the original paper but it is still weird. For eyes you'll notice things like them not pointing in the same direction (this isn't always super obvious). Another big thing to look at is the neck. Sometimes women will get Adam's Apples and men will…

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

Analyzing and Improving the Image Quality of StyleGAN — mentioned by axegon_

Tue, 08 Dec 2020 19:33:59 GMT

No second thought about it, stylegan2[1] takes the cake. [1] https://arxiv.org/abs/1912.04958

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

Analyzing and Improving the Image Quality of StyleGAN — mentioned by FL33TW00D

Sun, 22 Nov 2020 13:49:00 GMT

Seminal papers in this area AFAIK are StyleGAN1 and StyleGAN2: https://github.com/NVlabs/stylegan2 https://arxiv.org/abs/1912.04958

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

Analyzing and Improving the Image Quality of StyleGAN — mentioned by dtakuma

Fri, 07 Feb 2020 09:48:38 GMT

Seems like it has been vastly improved since then [1]. The results are much better than when originally posted in HN. [1] - https://arxiv.org/abs/1912.04958

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

Analyzing and Improving the Image Quality of StyleGAN — HN submission

Fri, 13 Dec 2019 04:03:20 GMT

Analyzing and Improving the Image Quality of StyleGAN

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