Generative Visual Manipulation on the Natural Image Manifold

people.eecs.berkeley.edu

77 points·huskyr··8 comments

https://www.youtube.com/watch?v=9c4z6YsBGQ0

Really cool, especially the morphing stuff which is amazingly convincing. On the other hand the drawing stuff, I just still can't get over the feeling that it's very similar to looking up best matches in a database, perhaps slightly morphed to better match the input. I guess that's more or less what it is..

Thank you guys for the interest. The interactive image generation interface as well as trained models are available at https://github.com/junyanz/iGAN. It is still under active development and let me know if you find bugs or would like to suggest new features.

The morphing is impressive. I wonder if something similar can morph between faces. It may even be possible to morph faces of parents and get something similar to the children of the parents, especially if that's set as the objective. Looking forward to release of the code.

Tom White has done a lot of fun work recently in this direction https://twitter.com/dribnet. You can absolutely do it with faces.

That's very cool, it's amazing what's become possible.

I thought of faces as well. Police sketch artists may be out of a job soon!

Cool... Is there anyway to combine this with a seam carving approach?

Great interface interface to GANs. Nice work

Reply on news.ycombinator.com