Improving Shape Deformation in Unsupervised Image-to-Image Translation — mentioned by gwern

Sat, 10 Nov 2018 13:59:23 GMT

(I contributed that one.) It's kind of annoying because when you first see CycleGAN, you think, 'this is amazing! I can use it for anything, like turning faces<->anime!' And then you actually try and you realize your photo<->anime CycleGAN is just learning the steganographic encoding because the roundtripping is too good ('wait, how does it reconstruct even the minor details of their hair so perfectly?') and so you wind up needing complicated regularization & tricks like "Improving Shape Deformation in Unsupervised Image-to-Image Translation" (https://arxiv.org/abs/1808.04325), Gokaslan et al…

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

Improving Shape Deformation in Unsupervised Image-to-Image Translation · HackerPapers discussions

Improving Shape Deformation in Unsupervised Image-to-Image Translation — mentioned by gwern