RenderGAN: Generating Realistic Labeled Data · HackerPapers discussions

RenderGAN: Generating Realistic Labeled Data — mentioned by dimatura

Fri, 10 May 2019 04:04:32 GMT

This could be used that way, and there is some precedent, e.g. in RenderGAN (https://arxiv.org/abs/1611.01331). Note the GAN part: that's why the "differentiable" part is important, so you can integrate rendering into a trainable network. Otherwise, you don't really need the "differentiable" part, and in fact using synthetic renderings from traditional, established renderers (both rasterizing and raytracing) has been a pretty active area for a while now. There's also some approaches like SUGAN (https://machinelearning.apple.com/2017/07/07/GAN.html), but those don't really use differentiable…

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

RenderGAN: Generating Realistic Labeled Data — HN submission

Tue, 27 Dec 2016 16:28:42 GMT

RenderGAN: Generating Realistic Labeled Data

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

RenderGAN: Generating Realistic Labeled Data — mentioned by spacehacker

Mon, 26 Dec 2016 08:57:21 GMT

FYI, the title has been changed from this being the first publication by Apple on arXiv to the title of the paper. It seems the technique presented in the paper was simultaneously discovered by Sixt et al: https://arxiv.org/abs/1611.01331 (Nov. 4th vs Nov. 15th)

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