公众号机器学习与生成对抗网络

CVPR 2021：110篇GAN论文（清单版）

点击上方“机器学习与生成对抗网络”，关注星标

获取有趣、好玩的前沿干货！

戳我，查看GAN的系列专辑~！

等你着陆！【GAN生成对抗网络】知识星球！

下述论文已分类打包好！超110篇，事实上仍有一些GAN论文未被包含入内……可见GAN在CVPR 2021仍十分火热。后台回复 2021GAN （长按红字、选中复制）获取分类、按文件夹汇总好的论文集，gan起来吧！！！

附带介绍版：超110篇！CVPR 2021最全GAN论文汇总梳理！

1 年龄迁移
2 发型迁移
3 妆容迁移
4 虚拟试衣
5 姿势迁移、人像合成
6 颜色控制
7 说话人驱动
8 人脸编辑
9 人脸识别
10 新视图生成
11 表征学习
12 解耦学习
13 主动学习
14 终身学习
15 迁移学习
16 少样本学习
17 单样本训练
18 多样化生成
19 多模态生成
20 新视图生成
21 行人重识别
22 人体运动合成
23 字体生成
24 仿真
25 医学图像
26 GAN的改进
27 结合VAE
28 结合transformer
29 模型压缩
30 散焦模糊检测
31 图像恢复、超分
32 图像去雨
33 图像修复
34 图像拼接融合
35 图像阴影
36 图像协调
37 图像分割
38 图像分类
39 图像转换
40 3D相关

一、年龄迁移

1，Continuous Face Aging via Self-estimated Residual Age Embedding

二、发型迁移

2，LOHO: Latent Optimization of Hairstyles via Orthogonalization https://github.com/dukebw/LOHO

三、妆容迁移

3，Spatially-invariant Style-codes Controlled Makeup Transfer https://github.com/makeuptransfer/SCGAN
4，Lipstick ain’t enough: Beyond Color Matching for In-the-Wild Makeup Transfer https://github.com/VinAIResearch/CPM

四、虚拟试衣

5，Disentangled Cycle Consistency for Highly-realistic Virtual Try-On
6，VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization

五、姿势迁移、人像合成

7，HumanGAN: A Generative Model of Human Images
8，MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation
9，PISE: Person Image Synthesis and Editing with Decoupled GAN

六、颜色控制

10，HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms https://github.com/mahmoudnafifi/HistoGAN HistoGAN

七、说话人驱动

11，Audio-Driven Emotional Video Portraits
12，Everything’s Talkin’: Pareidolia Face Reenactment
13，Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation
14，One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing
15，Flow-guided One-shot Talking Face Generation with a High-resolution Audio-visual Dataset

八、人脸图像编辑

16，Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing https://github.com/naver-ai/StyleMapGAN
17，High-Fidelity and Arbitrary Face Editing
18，Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs https://github.com/a514514772/hijackgan
19，Linear Semantics in Generative Adversarial Networks https://github.com/AtlantixJJ/LinearGAN
20，DeFLOCNet: Deep Image Editing via Flexible Low-level Controls https://github.com/KumapowerLIU/DeFLOCNet
21，L2M-GAN: Learning to Manipulate Latent Space Semantics for Facial Attribute Editing
22，One Shot Face Swapping on Megapixels

九、人脸识别

23、A 3D GAN for Improved Large-pose Facial Recognition
24、When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework https://github.com/Hzzone/MTLFace

十、新视图生成

25、Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization
26、Layout-Guided Novel View Synthesis from a Single Indoor Panorama https://github.com/bluestyle97/PNVS
27、ID-Unet: Iterative Soft and Hard Deformation for View Synthesis https://github.com/MingyuY/ Iterative-view-synthesis

十一、表征学习

28、Generative Hierarchical Features from Synthesizing Images https://genforce.github.io/ghfeat/

十二、解耦学习

29，Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation
30，Surrogate Gradient Field for Latent Space Manipulation
31，StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation
32，Unsupervised Disentanglement of Linear-Encoded Facial Semantics

十三、主动学习

33、Task-Aware Variational Adversarial Active Learning

十四、终身学习

34、Hyper-LifelongGAN: Scalable Lifelong Learning for Image Conditioned Generation

十五、迁移学习

35、Visualizing Adapted Knowledge in Domain Transfer https://github.com/houyz/DA_visualization
36、Efficient Conditional GAN Transfer with Knowledge Propagation across Classes https://github.com/mshahbazi72/cGANTransfer

十六、少样本学习

37，Few-shot Image Generation via Cross-domain Correspondence

十七、半监督学习

38、Mask-Embedded Discriminator with Region-based Semantic Regularization for Semi-Supervised Class-Conditional Image Synthesis
39、DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort

十八、单样本训练

40，Learning to Generate Novel Scene Compositions from Single Images and Videos
41，IMAGINE: Image Synthesis by Image-Guided Model Inversion

十九、多样化生成

42，DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network https://github.com/ruiliu-ai/DivCo
43，Diverse Semantic Image Synthesis via Probability Distribution Modeling https://github.com/tzt101/INADE.git

二十、多模态生成

44，Navigating the GAN Parameter Space for Semantic Image Editing
45，Context-Aware Layout to Image Generation with Enhanced Object Appearance https://github.com/wtliao/layout2img
46，House-GAN++: Generative Adversarial Layout Refinement Network towards Intelligent Computational Agent for Professional Architects https://ennauata.github.io/houseganpp/page.html
47，TediGAN: Text-Guided Diverse Image Generation and Manipulation https://github.com/weihaox/TediGAN
48、Semantic Palette: Guiding Scene Generation with Class Proportions
49、StEP: Style-based Encoder Pre-training for Multi-modal Image Synthesis

二十一、行人重识别

50、 Joint Generative and Contrastive Learning for Unsupervised Person Re-identification https://github.com/chenhao2345/GCL

二十二、人体运动合成

51、 Single-Shot Freestyle Dance Reenactment
52、 Scene-aware Generative Network for Human Motion Synthesis

二十三、字体生成

53、DG-Font: Deformable Generative Networks for Unsupervised Font Generation https://github.com/ecnuycxie/DG-Font

二十四、仿真

54、DriveGAN: Towards a Controllable High-Quality Neural Simulation

二十五、医学图像

55、GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review

二十六、GAN的改进

56，Directional GAN: A Novel Conditioning Strategy for Generative Networks
57，Image Generators with Conditionally-Independent Pixel Synthesis
58，Efficient Feature Transformations for Discriminative and Generative Continual Learning
59，A Sliced Wasserstein Loss for Neural Texture Synthesis
60，Regularizing Generative Adversarial Networks under Limited Data https://github.com/google/lecam-gan
61，Training Generative Adversarial Networks in One Stage
62，Posterior Promoted GAN with Distribution Discriminator for Unsupervised Image Synthesis
63、Adversarial Generation of Continuous Images https://universome.github.io/inr-gan
64，Partition-Guided GANs
65，Positional Encoding as Spatial Inductive Bias in GANs

二十七、结合VAE

66，Dual Contradistinctive Generative Autoencoder
67，Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder https://taldatech.github.io/soft-introvae-web

二十八、结合transformer

68，Taming Transformers for High-Resolution Image Synthesis https://git.io/JLlvY

二十九、模型压缩

69，Anycost GANs for Interactive Image Synthesis and Editing https://github.com/mit-han-lab/anycost-gan
70，Content-Aware GAN Compression

三十、散焦模糊检测

71，Self-generated Defocus Blur Detection via Dual Adversarial Discriminators https://github.com/shangcai1/SG

三十一、图像恢复、超分

72，GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution
73，GAN Prior Embedded Network for Blind Face Restoration in the Wild https://github.com/yangxy/GPEN
74，Progressive Semantic-Aware Style Transformation for Blind Face Restoration

三十二、图像去雨

75，Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation
76，From Rain Generation to Rain Removal https://github.com/hongwang01/VRGNet

三十三、图像修复

77，Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE https://github.com/USTC-JialunPeng/Diverse-Structure-Inpainting
78，Image Inpainting with External-internal Learning and Monochromic Bottleneck https://github.com/Tengfei-Wang/external-internal-inpainting
79，Image Inpainting Guided by Coherence Priors of Semantics and Textures
80，PD-GAN: Probabilistic Diverse GAN for Image Inpainting https://github.com/KumapowerLIU/PD-GAN

三十四、图像拼接融合

81，Bridging the Visual Gap: Wide-Range Image Blending

三十五、图像阴影

82，Towards High Fidelity Face Relighting with Realistic Shadows
83，From Shadow Generation to Shadow Removal

三十六、图像协调

84，Intrinsic Image Harmonization https://github.com/zhenglab/IntrinsicHarmony
85，Region-aware Adaptive Instance Normalization for Image Harmonization https://github.com/junleen/RainNe

三十七、图像分割

86，Repurposing GANs for One-shot Semantic Part Segmentation https://RepurposeGANs.github.io/
87，Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization https://nvtlabs.github.io/semanticGAN/

三十八、图像分类

88，Ensembling with Deep Generative Views

三十九、图像转换

89，Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation https://github.com/eladrich/pixel2style2pixel
90，Image-to-image Translation via Hierarchical Style Disentanglement https://github.com/imlixinyang/HiSD
91，Memory-guided Unsupervised Image-to-image Translation
92，ReMix: Towards Image-to-Image Translation with Limited Data
93，Spatially-Adaptive Pixelwise Networks for Fast Image Translation
94，The Spatially-Correlative Loss for Various Image Translation Tasks https://github.com/lyndonzheng/F-LSeSim
95，CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation
96，BalaGAN: Cross-Modal Image Translation Between Imbalanced Domains
97，Model-Aware Gesture-to-Gesture Translation
98，Saliency-Guided Image Translation
99，Teachers Do More Than Teach: Compressing Image-to-Image Models https://github.com/snap-research/CAT
100，Not just Compete, but Collaborate: Local Image-to-Image Translation via Cooperative Mask Prediction
101，Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation
102，CoMoGAN: continuous model-guided image-to-image translation https://github.com/cv-rits/CoMoGAN
103，Unbalanced Feature Transport for Exemplar-based Image Translation
104，Unpaired Image-to-Image Translation via Latent Energy Transport https://github.com/YangNaruto/latentenergy-transport

四十、3D相关

105，DECOR-GAN: 3D Shape Detailization by Conditional Refinement https://github.com/czq142857/DECOR-GAN
106，Inverting Generative Adversarial Renderer for Face Reconstruction
107，Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement
108，A 3D GAN for Improved Large-pose Facial Recognition
109，pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
110，StylePeople: A Generative Model of Fullbody Human Avatars saic-violet.github.io/style-people
111，Unsupervised 3D Shape Completion through GAN Inversion

猜您喜欢：