AAAI 2020 accepted papers on Image generation
86 of the 1,610 papers accepted at AAAI 2020 (5.3%) are on Image generation, compared with 4.1% at AAAI 2019. They fall into 7 topics.
See AAAI 2020 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
GANs · 28 papers
- FD-GAN: Generative Adversarial Networks with Fusion-Discriminator for Single Image Dehazing (319 citations)
- Attention Based Data Hiding with Generative Adversarial Networks (123 citations)
- Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software (114 citations)
- RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removal (96 citations)
- Generating Realistic Stock Market Order Streams (80 citations)
- CatGAN: Category-Aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generation (79 citations)
- Distilling Portable Generative Adversarial Networks for Image Translation (75 citations)
- Age Progression and Regression with Spatial Attention Modules (54 citations)
- A Character-Centric Neural Model for Automated Story Generation (42 citations)
- DeGAN: Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier (42 citations)
- CG-GAN: An Interactive Evolutionary GAN-Based Approach for Facial Composite Generation (39 citations)
- OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization (39 citations)
and 16 more in the interactive map.
Image restoration · 19 papers
- FFA-Net: Feature Fusion Attention Network for Single Image Dehazing (1,970 citations)
- Rethinking the Image Fusion: A Fast Unified Image Fusion Network based on Proportional Maintenance of Gradient and Intensity (637 citations)
- FusionDN: A Unified Densely Connected Network for Image Fusion (631 citations)
- Towards Ghost-Free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN (257 citations)
- EEMEFN: Low-Light Image Enhancement via Edge-Enhanced Multi-Exposure Fusion Network (235 citations)
- Region Normalization for Image Inpainting (198 citations)
- Natural Image Matting via Guided Contextual Attention (183 citations)
- When AWGN-Based Denoiser Meets Real Noises (146 citations)
- Coarse-to-Fine Hyper-Prior Modeling for Learned Image Compression (133 citations)
- Shallow Feature Based Dense Attention Network for Crowd Counting (130 citations)
- Region-Adaptive Dense Network for Efficient Motion Deblurring (117 citations)
- End-to-End Unpaired Image Denoising with Conditional Adversarial Networks (66 citations)
and 7 more in the interactive map.
Editing and style transfer · 12 papers
- Dynamic Instance Normalization for Arbitrary Style Transfer (204 citations)
- MarioNETte: Few-Shot Face Reenactment Preserving Identity of Unseen Targets (161 citations)
- Ultrafast Photorealistic Style Transfer via Neural Architecture Search (80 citations)
- GAN-Based Unpaired Chinese Character Image Translation via Skeleton Transformation and Stroke Rendering (76 citations)
- FLNet: Landmark Driven Fetching and Learning Network for Faithful Talking Facial Animation Synthesis (57 citations)
- FET-GAN: Font and Effect Transfer via K-shot Adaptive Instance Normalization (41 citations)
- EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfer (32 citations)
- Multimodal Structure-Consistent Image-to-Image Translation (25 citations)
- High Tissue Contrast MRI Synthesis Using Multi-Stage Attention-GAN for Segmentation (18 citations)
- Separate in Latent Space: Unsupervised Single Image Layer Separation (14 citations)
- FACT: Fused Attention for Clothing Transfer with Generative Adversarial Networks (11 citations)
- Benign Examples: Imperceptible Changes Can Enhance Image Translation Performance (1 citation)
Super-resolution · 10 papers
- Efficient Residual Dense Block Search for Image Super-Resolution (160 citations)
- Learning Light Field Angular Super-Resolution via a Geometry-Aware Network (147 citations)
- Pixel-Aware Deep Function-Mixture Network for Spectral Super-Resolution (124 citations)
- Image-Adaptive GAN Based Reconstruction (76 citations)
- Stereoscopic Image Super-Resolution with Stereo Consistent Feature (68 citations)
- High-Order Residual Network for Light Field Super-Resolution (49 citations)
- Joint Super-Resolution and Alignment of Tiny Faces (46 citations)
- Lightweight and Robust Representation of Economic Scales from Satellite Imagery (32 citations)
- Facial Attribute Capsules for Noise Face Super Resolution (27 citations)
- Image Formation Model Guided Deep Image Super-Resolution (15 citations)
Autoregressive and latent generation · 8 papers
- Learning to Incorporate Structure Knowledge for Image Inpainting (134 citations)
- Image Cropping with Composition and Saliency Aware Aesthetic Score Map (53 citations)
- CONAN: Complementary Pattern Augmentation for Rare Disease Detection (39 citations)
- PSENet: Psoriasis Severity Evaluation Network (32 citations)
- An Iterative Polishing Framework Based on Quality Aware Masked Language Model for Chinese Poetry Generation (25 citations)
- Attractive or Faithful? Popularity-Reinforced Learning for Inspired Headline Generation (17 citations)
- FPETS: Fully Parallel End-to-End Text-to-Speech System (6 citations)
- Recurrent Nested Model for Sequence Generation
Text-to-image diffusion · 7 papers
- Automatic Fact-Guided Sentence Modification (36 citations)
- Reinforcing an Image Caption Generator Using Off-Line Human Feedback (27 citations)
- Sentence Generation for Entity Description with Content-Plan Attention (21 citations)
- Complementary Auxiliary Classifiers for Label-Conditional Text Generation (19 citations)
- Open Domain Event Text Generation (8 citations)
- TemPEST: Soft Template-Based Personalized EDM Subject Generation through Collaborative Summarization (6 citations)
- Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation (5 citations)
