【CVPR2018】GAN相關論文彙總
CVPR彙總其他入口:
CVPR18 Detection文章選介(上)
CVPR18 Detection文章選介(下)
CVPR 2018 Person Re-ID相關論文
CVPR 2018 論文解讀集錦(持續更新)
CVPR2018 Visual Tracking 部分文章下載
1. 數目統計:
風格遷移/cycleGAN/domain adaptation
13篇
去霧/去遮擋/超畫素重建/Photo Enhancement
7篇
GAN最佳化
6篇
影象合成
10篇
人臉相關
7篇
姿態相關
4篇
行人重識別
3篇
其他類
<3篇
2. 分析:
今年GAN的山頭還是被domain adaptation和CycleGAN相關研究拿下,除此之外,影象合成和視覺病態問題也是GAN應用熱點,人臉,行人識別異軍突起,說明落地型工作開始增多。剩下幾篇都屬於挖坑型工作。
下面是正文,一己之力,難以覆蓋全域性,如有遺漏或者錯分的地方,歡迎提醒!!
—————————————————————————
風格遷移/cycleGAN/domain adaptation:
1.PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup:
Huiwen Chang (); Jingwan Lu (Adobe Research); Fisher Yu (UC Berkeley); Adam Finkelstein (Princeton Univ。)
2.CartoonGAN: Generative Adversarial Networks for Photo Cartoonization:
Yang Chen (Tsinghua Univ。); Yu-Kun Lai (Cardiff Univ。); Yong-Jin Liu ()
3.StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation:
Yunjey Choi (Korea Univ。); Minje Choi (Korea Univ。); Munyoung Kim (College of New Jersey); Jung-Woo Ha (NAVER); Sunghun Kim (Hong Kong Univ。 of Science and Technology); Jaegul Choo (Korea Univ。)
4.Generate to Adapt: Aligning Domains Using Generative Adversarial Networks:
Swami Sankaranarayanan (Univ。 of Maryland); Yogesh Balaji (Univ。 of Maryland); Carlos D。 Castillo (); Rama Chellappa (Univ。 of Maryland)
5.Re-Weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation:
Qingchao Chen (Unviersity College London); Yang Liu (Univ。 of Cambridge); Zhaowen Wang (Adobe); Ian Wassell (); Kevin Chetty ()
6.Multi-Content GAN for Few-Shot Font Style Transfer:
Samaneh Azadi (UC Berkeley); Matthew Fisher (Adobe); Vladimir G。 Kim (Adobe Research); Zhaowen Wang (Adobe); Eli Shechtman (Adobe Research); Trevor Darrell (UC Berkeley)
7.DA-GAN: Instance-Level Image Translation by Deep Attention Generative Adversarial Networks:
Shuang Ma (SUNY Buffalo); Jianlong Fu (); Chang Wen Chen (); Tao Mei ()
8.Adversarial Feature Augmentation for Unsupervised Domain Adaptation:
Riccardo Volpi (Istituto Italiano di Tecnologia); Pietro Morerio (Istituto Italiano di Tecnologia); Silvio Savarese (); Vittorio Murino (Istituto Italiano di Tecnologia)
9.Domain Generalization With Adversarial Feature Learning:
Haoliang Li (Nanyang Technological Univ。); Sinno Jialin Pan (Nanyang Technological Univ。); Shiqi Wang (City Univ。 of Hong Kong); Alex C。 Kot ()
10:Image to Image Translation for Domain Adaptation:
Zak Murez (UC San Diego); Soheil Kolouri (HRL Laboratories); David Kriegman (UC San Diego); Ravi Ramamoorthi (UC San Diego); Kyungnam Kim (HRL Laboratories)
11.Partial Transfer Learning With Selective Adversarial Networks:
Zhangjie Cao (Tsinghua Univ。); Mingsheng Long (Tsinghua Univ。); Jianmin Wang (); Michael I。 Jordan (UC Berkeley)
12.Duplex Generative Adversarial Network for Unsupervised Domain Adaptation:
Lanqing Hu (ICT, CAS); Meina Kan (); Shiguang Shan (Chinese Academy of Sciences); Xilin Chen ()
13.Conditional Generative Adversarial Network for Structured Domain Adaptation:
Weixiang Hong (Nanyang Technological Univ。); Zhenzhen Wang (Nanyang Technological Univ。); Ming Yang (Horizon Robotics); Junsong Yuan (Nanyang Technological Univ。)
去霧/去遮擋/超畫素重建/Photo Enhancement :
1.Single Image Dehazing via Conditional Generative Adversarial Network:
Runde Li (Nanjing Univ。 of Science and Technology ); Jinshan Pan (UC Merced); Zechao Li (Nanjing Univ。 of Science and Technology ); Jinhui Tang ()
2.DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks:
Orest Kupyn (Ukrainian Catholic Univ。); Volodymyr Budzan (Ukrainian Catholic Univ。); Mykola Mykhailych (Ukrainian Catholic Univ。); Dmytro Mishkin (Czech Technical Univ。); Jiří Matas ()
3.Deep Photo Enhancer: Unpaired Learning for Image Enhancement From Photographs With GANs:
Yu-Sheng Chen (National Taiwan Univ。); Yu-Ching Wang (National Taiwan Univ。); Man-Hsin Kao (National Taiwan Univ。); Yung-Yu Chuang (National Taiwan Univ。)
4.SeGAN: Segmenting and Generating the Invisible:
Kiana Ehsani (Univ。 of Washington); Roozbeh Mottaghi (Allen Institute for AI); Ali Farhadi (Allen Institute for AI, Univ。 of Washington)
5.Image Blind Denoising With Generative Adversarial Network Based Noise Modeling:
Jingwen Chen (Sun Yat-sen Univ。); Jiawei Chen (Sun Yat-sen Univ。); Hongyang Chao (Sun Yat-sen Univ。); Ming Yang ()
6.Attentive Generative Adversarial Network for Raindrop Removal From a Single Image:
Rui Qian (Peking Univ。); Robby T。 Tan (Yale-NUS College; National Univ。 of Singapore); Wenhan Yang (Peking Univ。); Jiajun Su (Peking Univ。); Jiaying Liu (Peking Univ。)
7.Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal:
Jifeng Wang (Nanjing Univ。 of Science and Technology); Xiang Li (Nanjing Univ。 of Science and Technology); Jian Yang (Nanjing Univ。 of Science and Technology)
GAN最佳化:
1.SGAN: An Alternative Training of Generative Adversarial Networks:
Tatjana Chavdarova (Idiap and EPFL); François Fleuret (Idiap Research Inst。)
2.Multi-Agent Diverse Generative Adversarial Networks:
Arnab Ghosh (Univ。 of Oxford); Viveka Kulharia (Univ。 of Oxford); Vinay P。 Namboodiri (Indian Inst。 of Technology Kanpur); Philip H。S。 Torr (Oxford); Puneet K。 Dokania (Univ。 of Oxford)
3.Generative Adversarial Image Synthesis With Decision Tree Latent Controller:
Takuhiro Kaneko (NTT); Kaoru Hiramatsu (NTT); Kunio Kashino (NTT)
4.Unsupervised Deep Generative Adversarial Hashing Network:
Kamran Ghasedi Dizaji (Univ。 of Pittsburgh); Feng Zheng (Univ。 of Pittsburgh); Najmeh Sadoughi (UT Dallas); Yanhua Yang (Xidian Univ。); Cheng Deng (Xidian Univ。); Heng Huang (Univ。 of Pittsburgh)
5.Global Versus Localized Generative Adversarial Nets:
Guo-Jun Qi (Univ。 of Central Florida); Liheng Zhang (Univ。 of Central Florida); Hao Hu (Univ。 of Central Florida); Marzieh Edraki (Univ。 of Central Florida ); Jingdong Wang (Microsoft Research); Xian-Sheng Hua (Microsoft Research)
6.GAGAN: Geometry-Aware Generative Adversarial Networks:
Jean Kossaifi (Imperial College London); Linh Tran (Imperial College London); Yannis Panagakis (); Maja Pantic (Imperial College London)
影象合成:
1.ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing:
Chen-Hsuan Lin (Carnegie Mellon Univ。); Ersin Yumer (Argo AI); Oliver Wang (Adobe); Eli Shechtman (Adobe Research); Simon Lucey ()
2.SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis:
Wengling Chen (Georgia Inst。 of Technology); James Hays (Georgia Tech)
3.Translating and Segmenting Multimodal Medical Volumes With Cycle- and Shape-Consistency Generative Adversarial Network:
Zizhao Zhang (Univ。 of Florida); Lin Yang (); Yefeng Zheng (Simens )
4.High-Resolution Image Synthesis and Semantic Manipulation With Conditional GANs:
Ting-Chun Wang (NVIDIA); Ming-Yu Liu (NVIDIA); Jun-Yan Zhu (UC Berkeley); Andrew Tao (NVIDIA); Jan Kautz (NVIDIA); Bryan Catanzaro (NVIDIA)
5.TextureGAN: Controlling Deep Image Synthesis With Texture Patches:
Wenqi Xian (); Patsorn Sangkloy (Georgia Inst。 of Technology); Varun Agrawal (); Amit Raj (Georgia Inst。 of Technology); Jingwan Lu (Adobe Research); Chen Fang (Adobe Research); Fisher Yu (UC Berkeley); James Hays (Georgia Tech)
6.Eye In-Painting With Exemplar Generative Adversarial Networks:
Brian Dolhansky (Facebook); Cristian Canton Ferrer (Facebook)
7.Photographic Text-to-Image Synthesis With a Hierarchically-Nested Adversarial Network:
Zizhao Zhang (Univ。 of Florida); Yuanpu Xie (Univ。 of Florida); Lin Yang ()
8.Logo Synthesis and Manipulation With Clustered Generative Adversarial Networks:
Alexander Sage (ETH Zürich); Eirikur Agustsson (ETH Zürich); Radu Timofte (ETH Zürich); Luc Van Gool (ETH Zürich)
9.Cross-View Image Synthesis Using Conditional GANs:
Krishna Regmi (Univ。 of Central Florida); Ali Borji (Univ。 of Central Florida)
10.AttnGAN: Fine-Grained Text to Image Generation With Attentional Generative Adversarial Networks:
Tao Xu (Lehigh Univ。); Pengchuan Zhang (); Qiuyuan Huang (); Han Zhang (Rutgers); Zhe Gan (); Xiaolei Huang (Lehigh ); Xiaodong He ()
人臉相關:
1.Finding Tiny Faces in the Wild With Generative Adversarial Network:
Yancheng Bai (KAUST/Iscas); Yongqiang Zhang (Harbin Inst。 of Technology/KAUST); Mingli Ding (); Bernard Ghanem ()
2.Learning Face Age Progression: A Pyramid Architecture of GANs:
Hongyu Yang (Beihang Univ。); Di Huang (); Yunhong Wang (); Anil K。 Jain (MSU)
3.Super-FAN: Integrated Facial Landmark Localization and Super-Resolution
of Real-World Low Resolution Faces in Arbitrary Poses With GANs:
Adrian Bulat (); Georgios Tzimiropoulos ()
4.Face Aging With Identity-Preserved Conditional Generative Adversarial Networks:
Zongwei Wang (); Xu Tang (Baidu); Weixin Luo (ShanghaiTech Univ。); Shenghua Gao (ShanghaiTech Univ。)
5.Towards Open-Set Identity Preserving Face Synthesis:
Jianmin Bao (Univ。 of Science and Technology of China); Dong Chen (Microsoft Research Asia); Fang Wen (); Houqiang Li (); Gang Hua
(Microsoft Research)
6.Weakly Supervised Facial Action Unit Recognition Through Adversarial Training:
Guozhu Peng (Univ。 of Science and Technology of China); Shangfei Wang ()
7.FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis:
Yujun Shen (Chinese Univ。 of Hong Kong); Ping Luo (Chinese Univ。 of Hong Kong); Junjie Yan (); Xiaogang Wang (Chinese Univ。 of Hong Kong); Xiaoou Tang (Chinese Univ。 of Hong Kong)
人體姿態相關:
1.GANerated Hands for Real-Time 3D Hand Tracking From Monocular RGB:
Franziska Mueller (MPI Informatics); Florian Bernard (MPI Informatics); Oleksandr Sotnychenko (MPI Informatics); Dushyant Mehta (MPI Informatics); Srinath Sridhar (); Dan Casas (MPI Informatics); Christian Theobalt (MPI Informatics)
2.Multistage Adversarial Losses for Pose-Based Human Image Synthesis:
Chenyang Si (Inst。 of Automation, Chinese Academy of Sciences); Wei Wang (); Liang Wang (); Tieniu Tan (NLPR)
3.Deformable GANs for Pose-Based Human Image Generation:
Aliaksandr Siarohin (DISI, Univ。 of Trento); Enver Sangineto (Univ。 of Trento); Stéphane Lathuilière (INRIA); Nicu Sebe (Univ。 of Trento)
4.Social GAN: Socially Acceptable Trajectories With Generative Adversarial Networks:
Agrim Gupta (Stanford Univ。); Justin Johnson (Stanford Univ。); Li Fei-Fei (Stanford Univ。); Silvio Savarese (); Alexandre Alahi (EPFL)
行人重識別:
1.Person Transfer GAN to Bridge Domain Gap for Person Re-Identification:
Longhui Wei (Peking Univ。); Shiliang Zhang (Peking Univ。); Wen Gao (); Qi Tian ()
2.Disentangled Person Image Generation:
Liqian Ma (KU Leuven); Qianru Sun (MPI Informatics); Stamatios Georgoulis (KU Leuven); Luc Van Gool (KU Leuven); Bernt Schiele (MPI Informatics); Mario Fritz (MPI Informatics)
3.Image-Image Domain Adaptation With Preserved Self-Similarity and Domain-Dissimilarity for Person Re-Identification:
Weijian Deng (Univ。 of Chinese Academy); Liang Zheng (UT San Antonio); Qixiang Ye (); Guoliang Kang (Univ。 of Technology Sydney); Yi Yang (); Jianbin Jiao ()
目標跟蹤:
1.VITAL: VIsual Tracking via Adversarial Learning:
Yibing Song (Tencent AI Lab); Chao Ma (); Xiaohe Wu (Harbin Inst。 of Technology); Lijun Gong (City Univ。 of Hong Kong); Linchao Bao (Tencent AI Lab); Wangmeng Zuo (Harbin Inst。 of Technology); Chunhua Shen (Univ。 of Adelaide); Rynson W。H。 Lau (City Univ。 of Hong Kong); Ming-Hsuan Yang (UC Merced)
2.SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation:
Xiao Wang (Anhui Univ。); Chenglong Li (Anhui Univ。); Bin Luo (); Jin Tang ()
目標檢測:
1.Generative Adversarial Learning Towards Fast Weakly Supervised Detection:
Yunhan Shen (Xiamen Univ。); Rongrong Ji (); Shengchuan Zhang (); Wangmeng Zuo (Harbin Inst。 of Technology); Yan Wang (Microsoft)
特徵可解釋性:
1.Visual Feature Attribution Using Wasserstein GANs:
Christian F。 Baumgartner (ETH Zürich); Lisa M。 Koch (ETH Zürich); Kerem Can Tezcan (ETH Zürich); Jia Xi Ang (ETH Zürich); Ender Konukoglu (ETH Zürich)
影象檢索:
1.HashGAN: Deep Learning to Hash With Pair Conditional Wasserstein GAN:
Yue Cao (Tsinghua Univ。); Bin Liu (Tsinghua Univ。); Mingsheng Long (Tsinghua Univ。); Jianmin Wang ()
影片合成:
1.Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks:
Wei Xiong (Univ。 of Rochester); Wenhan Luo (Tencent AI Lab); Lin Ma (Tencent AI Lab); Wei Liu (); Jiebo Luo (Univ。 of Rochester)
2.MoCoGAN: Decomposing Motion and Content for Video Generation:
Sergey Tulyakov (); Ming-Yu Liu (NVIDIA); Xiaodong Yang (NVIDIA); Jan Kautz (NVIDIA)