【CVPR2019】GAN相關論文匯總
往年入口：
Xf Mao：【CVPR2018】GAN相關論文匯總
分析：今年CVPR上GAN依然是最大贏家，而且有往多個新領域發展的趨勢。今年GAN最熱門的應用領域在風格遷移/image-to-image translation，以及 domain adaptation 兩個大方向，另外用GAN挖新坑的工作也不少。
這次整理的比較全，開源論文附源碼鏈接，有信息不全或紕漏請指出！
一、 GAN改進
Label-Noise Robust Generative Adversarial Networks [code]
Spatial Fusion GAN for Image Synthesis
Sliced Wasserstein Generative Models [code]
Sphere Generative Adversarial Network Based on Geometric Moment Matching [code]
A Style-Based Generator Architecture for Generative Adversarial Networks [code]
Parallel Optimal Transport GAN
Mixture Density Generative Adversarial Networks
FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery [code]
Conditional Adversarial Generative Flow for Controllable Image Synthesis
Max-Sliced Wasserstein Distance and Its Use for GANs
On Stabilizing Generative Adversarial Training With Noise
Feedback Adversarial Learning: Spatial Feedback for Improving Generative Adversarial Networks
Self-Supervised GANs via Auxiliary Rotation Loss [code]
二、圖像合成：
1. 文字->圖像
MirrorGAN: Learning Text-To-Image Generation by Redescription
Semantics Disentangling for Text-to-Image Generation
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis
StoryGAN: A Sequential Conditional GAN for Story Visualization [code]
Text2Scene: Generating Compositional Scenes from Textual Descriptions [code]
Object-Driven Text-To-Image Synthesis via Adversarial Training
2. 風格遷移/Image-to-Image Translation
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis [code]
Latent Filter Scaling for Multimodal Unsupervised Image-to-Image Translation
Semantic Image Synthesis with Spatially-Adaptive Normalization [code] [demo]
Progressive Pose Attention Transfer for Person Image Generation [code] [demo]
Attention-aware Multi-stroke Style Transfer [code]
Example-Guided Style-Consistent Image Synthesis from Semantic Labeling
Im2Pencil: Controllable Pencil Illustration From Photographs [code]
Deep Network Interpolation for Continuous Imagery Effect Transition [code]
Homomorphic Latent Space Interpolation for Unpaired Image-to-image Translation [code]
Multi-Channel Attention Selection GAN With Cascaded Semantic Guidance for Cross-View Image Translation [code]
Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping
CollaGAN: Collaborative GAN for Missing Image Data Imputation
Towards Instance-level Image-to-Image Translation
Reversible GANs for Memory-Efficient Image-To-Image Translation [code]
Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-To-Image Translation [code]
TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation
TraVeLGAN: Image-To-Image Translation by Transformation Vector Learning
A Content Transformation Block For Image Style Transfer [code]
Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation
APDrawingGAN: Generating Artistic Portrait Drawings from Face Photos with Hierarchical GANs
WarpGAN: Automatic Caricature Generation [code]
3. domain adaptation
CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency
Blending-Target Domain Adaptation by Adversarial Meta-Adaptation Networks [code]
DLOW: Domain Flow for Adaptation and Generalization
Taking a Closer Look at Domain Shift: Category-Level Adversaries for Semantics Consistent Domain Adaptation [code]
ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation [code]
Gotta Adapt Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild
Universal Domain Adaptation [code]
Domain-Symmetric Networks for Adversarial Domain Adaptation
Unsupervised Domain Adaptation for ToF Data Denoising With Adversarial Learning
Bidirectional Learning for Domain Adaptation of Semantic Segmentation [code]
4. Inpainting
Pluralistic Image Completion [code] [demo]
Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting [code]
Foreground-aware Image Inpainting
5. 圖像增強：超分辨/去霧/去雨/去模糊
Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning
Enhanced Pix2pix Dehazing Network [code]
Image Super-Resolution by Neural Texture Transfer
Unsupervised Domain-Specific Deblurring via Disentangled Representations
三、語義分割/圖像理解
All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation
Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach
Scene Graph Generation with External Knowledge and Image Reconstruction
Learning Words by Drawing Images
Adversarial Structure Matching for Structured Prediction Tasks
Not All Areas Are Equal: Transfer Learning for Semantic Segmentation via Hierarchical Region Selection
KE-GAN: Knowledge Embedded Generative Adversarial Networks for Semi-Supervised Scene Parsing
四、人臉/行人
1. 人臉/行人生成
Mask-Guided Portrait Editing with Conditional GANs
Text Guided Person Image Synthesis
Dense Intrinsic Appearance Flow for Human Pose Transfer
Hierarchical Cross-Modal Talking Face Generation with Dynamic Pixel-Wise Loss
Attribute-Aware Face Aging With Wavelet-Based Generative Adversarial Networks
2. 人臉識別
Decorrelated Adversarial Learning for Age-Invariant Face Recognition
R 3 Adversarial Network for Cross Model Face Recognition
Multi-adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection
3. 人臉重建
GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction [code]
五、視頻合成
Predicting Future Frames using Retrospective Cycle GAN
Video Generation from Single Semantic Label Map
Inserting Videos into Videos
Event-based High Dynamic Range Image and Very High Frame Rate Video Generation using Conditional Generative Adversarial Networks
End-To-End Time-Lapse Video Synthesis From a Single Outdoor Image
GIF2Video: Color Dequantization and Temporal Interpolation of GIF Images
Animating Arbitrary Objects via Deep Motion Transfer [code]
六、圖像編輯
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing [code]
Mask-Guided Portrait Editing with Conditional GANs
Constrained Generative Adversarial Networks for Interactive Image Generation
七、Zero-Shot learning
Gradient Matching Generative Networks for Zero-Shot Learning
Generative Dual Adversarial Network for Generalized Zero-shot Learning
八、模型壓縮
Towards Optimal Structured CNN Pruning via Generative Adversarial Learning [code]
九、Caption
Unsupervised Image Captioning [code]
MSCap: Multi-Style Image Captioning with Unpaired Stylized Text
Adversarial Inference for Multi-Sentence Video Description
Adversarial Semantic Alignment for Improved Image Captions
十、無監督聚類
Balanced Self-Paced Learning for Generative Adversarial Clustering Network
十一、3D合成
Synthesizing 3D Shapes From Silhouette Image Collections Using Multi-Projection Generative Adversarial Networks
RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion [code]
Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds Using Convolutional Neural Networks
十二、識別
SketchGAN: Joint Sketch Completion and Recognition with Generative Adversarial Network
Joint Discriminative and Generative Learning for Person Re-identification
Enhancing TripleGAN for Semi-Supervised Conditional Instance Synthesis and Classification
f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
十三、對抗攻擊
Rob-GAN: Generator, Discriminator and Adversarial Attacker [code]
MeshAdv: Adversarial Meshes for Visual Recognition
十四、New Applications
Listen to the Image
How to make a pizza: Learning a compositional layer-based GAN model
Image Generation from Layout
BeautyGlow: On-Demand Makeup Transfer Framework with Reversible Generative Network [code] [demo]
X2CT-GAN: Reconstructing CT From Biplanar X-Rays With Generative Adversarial Networks
A Generative Adversarial Density Estimator
SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints
DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition
OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations
推薦閱讀：
