Generative Adversarial Text to Image Synthesis · HackerPapers discussions

Generative Adversarial Text to Image Synthesis — mentioned by nl

Thu, 08 Dec 2016 02:42:04 GMT

Because that isn't true? Looking at the first thing (GANs): developed by Ian Goodfellow, who is now at OpenAI. The first linked paper (https://arxiv.org/pdf/1605.05396v2.pdf) is out of University of Michigan and Max Planck Institute. The second (https://phillipi.github.io/pix2pix/) is out of Berkeley, the third (https://arxiv.org/pdf/1609.04802v3.pdf) is out of Twitter (which I guess counts as a rich American tech company). Google Brain/DeepMind/FAIR/MS Research do great work, but there is plenty of great work elsewhere too. For example, just yesterday an implementation[1] of Fast Layer…

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

Generative Adversarial Text to Image Synthesis — mentioned by dietrichepp

Fri, 21 Oct 2016 01:25:40 GMT

This article is best juxtaposed with articles about image synthesis: * Wave Function Collapse image generator https://github.com/mxgmn/WaveFunctionCollapse * Image Synthesis from Yahoo's open_nsfw: https://open_nsfw.gitlab.io * Generative Adversarial Text to Image Synthesis: https://arxiv.org/abs/1605.05396 Put another way, when I look at the McMansions at 10 on the scale, it looks to me like the kind of output you get when you just feed a bunch of pictures of houses into a neural network without feeding in any of the cultural or aesthetic context. Things like the large garages and roofs look…

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

Generative Adversarial Text to Image Synthesis — HN submission

Mon, 08 Aug 2016 00:26:29 GMT

Generative Adversarial Text to Image Synthesis

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

Generative Adversarial Text to Image Synthesis — mentioned by lars

Sat, 11 Jun 2016 20:07:47 GMT

> One main thing it lacks is imagination. [...] For example, if I ask you to imagine a Guitar playing Dolphin, you could imagine it and even recognize it from a cartoon even though you have never seen it in your life before. Not so for Deep Learning These days one should be careful when claiming things deep learning can't do. There are in fact systems that can imagine things it has never seen before. Here's an example. It takes any text, and imagines an image for it: https://github.com/emansim/text2image Here's a more recent example, with even higher quality images…

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

Generative Adversarial Text to Image Synthesis — mentioned by tpm

Mon, 23 May 2016 09:19:53 GMT

and also programs that do the reverse: http://arxiv.org/abs/1605.05396

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