2015년 석사 입학 후 연말쯤에 소소하게 했던 프로젝트. 예전 인터뷰했던게 생각나서 공유. 인터뷰 link 0. Google HackFair는 구글 기술을 이용해서 만든 다양한 결과물들을 전시하고 공유하는 행사입니다. 지난 12월 5일, 프로젝트 참가자분들은 안드로이드, Cardboard, TensorFlow 등 다양한 구글 기술을 사용한 재미있는 프로젝트를 전시하고 풍성한 볼거리와 기술력 그리고 범상치 않은 업력(?)을

StarGAN : accepted as CVPR2018 oral presentation. github arxiv (a) Each domain shift needs generators. (b) Share one generator and use latent code of each domain The previous limitation of pix2pix, DTN, CycleGAN & DiscoGAN, BicycleGAN is that they only handle two domains: the source and the target. But, there are

Limitations of pix2pix, DTN, DiscoGAN & CycleGAN? They produce single answer. They are deterministic models. Translates an image in one-to-one Paired set, One-to-One : pix2pix (CVPR2017) Unpaired set, One-to-One : DTN (ICLR2017), CycleGAN (ICCV2017) Paired set, One-to-Many : ??? BicycleGAN: Toward Multimodal Image-to-Image Translation (NIPS2017) BicycleGAN github Easy approach: Adopt stochastically sampled noise $N(

Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (CycleGAN) from UC Berkeley (pix2pix upgrade) & Learning to Discover Cross-Domain Relations with Generative Adversarial Networks (DiscoGAN) from SK T-Brain DiscoGAN & CycleGAN Almost Identical concept. DiscoGAN came 15 days earlier. Low resolution ($64 \times 64$) CycleGAN has better qualitative results ($256 \times

2. Unsupervised Cross-Domain Image Generation (DTN) published to ICLR2017 by Yaniv Taigman, Adam Polyak, Lior Wolf Learn $ G: S \rightarrow T $ of two related domains, $ S $ and $ T $ without labels! (labels of images are usually expensive) Baseline model $ D $ : discriminator, $ G $ : generator, $ f $ : context encoder. outputs feature. (128-dim) \begin{equation}

Image-to-Image Translation with Conditional Adversarial Networks (pix2pix) published to CVPR2017 by Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros Learn pair-wise images of $S$ and $T$ like below BW & Color image Street Scene & Label Facade & Label Aerial & Map Day & Night Edges & Photo source

Problem statement of Image Translation Learn $G: (S \rightarrow T)$ $G$ that convert an image of source domain $S$ to an image of target domain $T$ Domain Adaptation/Transfer of an image. Paired and Unpaired dataset Image Translation: $S$ and $T$ are pair-wise labeled in dataset Image Translation: $S$ and

Junho Cho, Sangdoo Yun, Kyoungmu Lee and Jin Young Choi, PaletteNet: Image Recolorization with Given Color Palette The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, NITRE2017, July, 2017. poster better resolution paper