AAAI 2021 accepted papers on Image generation
64 of the 1,654 papers accepted at AAAI 2021 (3.9%) are on Image generation, compared with 5.3% at AAAI 2020. They fall into 7 topics.
See AAAI 2021 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 · 17 papers
- Improved Consistency Regularization for GANs (105 citations)
- CardioGAN: Attentive Generative Adversarial Network with Dual Discriminators for Synthesis of ECG from PPG (87 citations)
- GAN Ensemble for Anomaly Detection (72 citations)
- StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding (67 citations)
- IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks (47 citations)
- Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Network (46 citations)
- SSD-GAN: Measuring the Realness in the Spatial and Spectral Domains (42 citations)
- ExGAN: Adversarial Generation of Extreme Samples (40 citations)
- Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis (40 citations)
- TextGAIL: Generative Adversarial Imitation Learning for Text Generation (30 citations)
- Predictive Adversarial Learning from Positive and Unlabeled Data (29 citations)
- Spectral Distribution Aware Image Generation (26 citations)
and 5 more in the interactive map.
Editing and style transfer · 15 papers
- Few-shot Font Generation with Localized Style Representations and Factorization (106 citations)
- HiGAN: Handwriting Imitation Conditioned on Arbitrary-Length Texts and Disentangled Styles (57 citations)
- FaceController: Controllable Attribute Editing for Face in the Wild (40 citations)
- Self-Supervised Sketch-to-Image Synthesis (36 citations)
- MangaGAN: Unpaired Photo-to-Manga Translation Based on The Methodology of Manga Drawing (28 citations)
- Sketch Generation with Drawing Process Guided by Vector Flow and Grayscale (24 citations)
- One-shot Face Reenactment Using Appearance Adaptive Normalization (23 citations)
- Stylized Dialogue Response Generation Using Stylized Unpaired Texts (23 citations)
- Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation (21 citations)
- Analogical Image Translation for Fog Generation (20 citations)
- Toward Realistic Virtual Try-on Through Landmark Guided Shape Matching (17 citations)
- The Style-Content Duality of Attractiveness: Learning to Write Eye-Catching Headlines via Disentanglement (12 citations)
and 3 more in the interactive map.
Image restoration · 12 papers
- EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining (114 citations)
- Towards Domain Invariant Single Image Dehazing (51 citations)
- Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal (50 citations)
- End-to-End Differentiable Learning to HDR Image Synthesis for Multi-exposure Images (39 citations)
- Dual-Octave Convolution for Accelerated Parallel MR Image Reconstruction (31 citations)
- Efficient Deep Image Denoising via Class Specific Convolution (17 citations)
- Learned Bi-Resolution Image Coding using Generalized Octave Convolutions (16 citations)
- Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty (12 citations)
- SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration (11 citations)
- MIEHDR CNN: Main Image Enhancement based Ghost-Free High Dynamic Range Imaging using Dual-Lens Systems (7 citations)
- Deep Low-Contrast Image Enhancement using Structure Tensor Representation (3 citations)
- Modeling Deep Learning Based Privacy Attacks on Physical Mail (1 citation)
Autoregressive and latent generation · 11 papers
- Symbolic Music Generation with Transformer-GANs (64 citations)
- SongMASS: Automatic Song Writing with Pre-training and Alignment Constraint (55 citations)
- High-Resolution Deep Image Matting (52 citations)
- TaLNet: Voice Reconstruction from Tongue and Lip Articulation with Transfer Learning from Text-to-Speech Synthesis (18 citations)
- Spherical Image Generation from a Single Image by Considering Scene Symmetry (17 citations)
- Exploiting Relationship for Complex-scene Image Generation (14 citations)
- Probing Product Description Generation via Posterior Distillation (14 citations)
- Audio-Visual Localization by Synthetic Acoustic Image Generation (10 citations)
- Aspect-Level Sentiment-Controllable Review Generation with Mutual Learning Framework (8 citations)
- Flow-based Generative Models for Learning Manifold to Manifold Mappings (7 citations)
- A Spatial Regulated Patch-Wise Approach for Cervical Dysplasia Diagnosis (6 citations)
Text-to-image diffusion · 5 papers
- TIME: Text and Image Mutual-Translation Adversarial Networks (40 citations)
- Fact-Enhanced Synthetic News Generation (25 citations)
- Open Domain Dialogue Generation with Latent Images (21 citations)
- Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View (18 citations)
- Sketch and Customize: A Counterfactual Story Generator (10 citations)
