Adobe Research » PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup
We introduce an automatic method for editing a portrait photo so that the subject appears to be wearing makeup in the style of another person in a reference photo. Our unsupervised learning approach relies on a new framework of cycle-consistent generative adversarial networks. Different from the image domain transfer problem, our style transfer problem involves two asymmetric functions: a forward
jingwan-lu
Jingwan joined Adobe Research in 2014. She is currently leading a team of research scientists and engineers with the vision to disrupt visual content creation with big data and generative AI. Her research interests include generative image modeling (GANs, etc.), computational photography, digital human and data-driven artistic content creation. She has over 30 issued patents and over 40 publicatio
Hailin Jin
Hailin is a senior principal scientist at Adobe. He received his Master of Science and Doctor of Science degrees in electrical engineering from Washington University in Saint Louis in 2000 and 2003, respectively. Between fall 2003 and fall 2004, he was a postdoctoral researcher at the Computer Science Department, University of California at Los Angeles. His current research interests include: deep
Imagine. Explore. Invent.
Adobe and MIT researchers are making AI image generation 30x faster Researchers from Adobe and MIT have developed a new AI model that generates images 30 times faster. This advancement not only has the potential to speed up the entire AI generation pipeline but also reduces costs and energy consumption. Adobe Research at CVPR 2024 Adobe Research is proud to be one of the sponsors of CVPR 2024. Che
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
処理を実行中です
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
