Home

Info Title: Progressive Pose Attention Transfer for Person Image Generation Task: Image Generation Author: Zhen Zhu , Tengteng Huang , Baoguang Shi, Miao Yu , Bofei Wang , Xiang Bai Arxiv: 1904.03349 Published: CVPR 2019 Highlights We propose a progressive pose attention transfer network to address the challenging task of ...

Info Title: Bag of Tricks for Image Classification with Convolutional Neural Networks Task: Image Classification Author: Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, Mu Li Arxiv: 1812.01187 Abstract Much of the recent progress made in image classification research can be credited to training procedure refinements, su...

Info Title: TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation Task: Image-to-Image Translation Author: Wayne Wu, Kaidi Cao, Cheng Li, Chen Qian, Chen Change Loy Arxiv: 1904.09571 Published: CVPR 2019 Abstract Unsupervised image-to-image translation aims at learning a mapping between two visual domains. However, lea...

Info Title: Deep Image Prior Task: Low-level Vision Author: Dmitry Ulyanov, Andrea Vedaldi, Victor Lempitsky Arxiv: 1711.10925 Published: CVPR 2018 Highlights Contrary to the belief that learning is necessary for building good image priors, a great deal of image statistics are captured by the structure of a convolutional image gen...

Info Title: Semantics Disentangling for Text-to-Image Generation Task: Text-to-Image Author: Guojun Yin, Bin Liu, Lu Sheng, Nenghai Yu, Xiaogang Wang, Jing Shao Arxiv: 1904.01480 Published: CVPR 2019 Highlights Distill Semantic Commons from Text- The proposed SD-GAN distills semantic commons from the linguistic descriptions, based ...

Info Title: Image Generation from Layout Task: Image Generation Author: Bo Zhao Lili Meng Weidong Yin Leonid Sigal Date: Nov. 2018 Arxiv: 1811.11389 Published: CVPR 2019 Abstract Despite significant recent progress on generative models, controlled generation of images depicting multiple and complex object layouts is still a diff...

pix2pixHD - Ting-Chun Wang - CVPR 2018 Title: High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs Author: Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, A. Tao, J. Kautz, and B. Catanzaro Date: Nov. 2017. Arxiv: 1711.11585 Published: CVPR 2018 Coarse-to-fine generator We first train a residual network G1 on ...

pix2pix(PatchGAN) - Isola - CVPR 2017 Title: Image-to-Image Translation with Conditional Adversarial Networks Author: P. Isola, J.-Y. Zhu, T. Zhou, and A. A. Efros Date: Nov. 2016. Arxiv: 1611.07004 Published: CVPR 2017 Example results on several image-to-image translation problems. In each case we use the same architecture and obj...

This is the third part of Deep Generative Models(Part 1 and Part 2). We’ll focus on Generative Adversarial Networks(GANs) in this post. GANs: Generative Adversarial Network Generative Adversarial Networks - Goodfellow - NIPS 2014 Title: Generative Adversarial Networks Author: I. J. Goodfellow et al Date: Jun. 2014. Arxiv: 1406.2661 ...

This is the second part of Deep Generative Model(Part 1) Series. We’ll focus on Flow-based models in this post. There are two types of flow: normalizing flow and autoregressive flow. fully-observed graphical models: PixelRNN & PixelCNN -> PixelCNN++, WaveNet(audio) latent-variable invertible models(Flow-based): NICE, Real NVP ->...