Diverse Image Synthesis from Semantic Layouts via Conditional IMLE · HackerPapers discussions

Diverse Image Synthesis from Semantic Layouts via Conditional IMLE — mentioned by sillysaurusx

Sun, 13 Oct 2019 15:40:16 GMT

When you hear autoregressive model, think “predicting a sequence”. These are good for text to speech since you can say “given some text, generate a spectrogram.” GPT-2 is probably the most impressive example of autoregressive techniques (I think). GANs, and especially stylegan, are good for generating high quality images up to 1024x1024. These take about 5 weeks to train and $1k of GCE credits. The dataset size is around 70k photos for FFHQ. Mode collapse is a concern, which is when the discriminator wins the game and the generator fails to generate anything that can fool it. Stylegan has…

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

Diverse Image Synthesis from Semantic Layouts via Conditional IMLE — HN submission

Fri, 30 Aug 2019 13:30:18 GMT

Diverse Image Synthesis from Semantic Layouts via Conditional IMLE

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

Diverse Image Synthesis from Semantic Layouts via Conditional IMLE — HN submission

Sun, 02 Dec 2018 00:42:16 GMT

Diverse Image Synthesis from Semantic Layouts via Conditional IMLE

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