Visual Attribute Transfer through Deep Image Analogy

https://arxiv.org/abs/1512.03385 Deep Residual Learning for Image Recognition Citation 4000+. Milestone of image recognition. https://arxiv.org/abs/1502.01852 Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. Also known as PreLU, citation 1600+. The initialization scheme is widely adapted by a lot of following works. Those are the most influential ones, all come from Kaiming He. He is now in FAIR, and keeps very good publication record, with works like MASK-RCNN, but that doesn't really count as purely Chinese contribution, so we skipped here. Some recent memory: 1. https://arxiv.org/abs/1703.06211 2. https://arxiv.org/abs/1709.01507 3. https://arxiv.org/abs/1707.01083 4. https://arxiv.org/pdf/1608.06993 5. https://arxiv.org/abs/1705.01088 Those are all good papers.

One way to make CG images more real is to pass them through a neural network. Some GANs can do that. Apple had a paper about synthesizing eyes using such a process. Here: "Improving the Realism of Synthetic Images" https://machinelearning.apple.com/2017/07/07/GAN.html Also: "Visual Attribute Transfer through Deep Image Analogy" https://arxiv.org/abs/1705.01088 (this paper even shows a refined CG Mona Lisa)

Deep learning based style transfer that got viral a year or two ago was worse than this 2008 result, especially worse for that hone application to portraits. The hype was nowhere near just because there's no deepness. I admit that https://arxiv.org/abs/1705.01088 this beats everything and is extremely powerful and simple but the hype for deep things seems a bit too strong.