AAAI 2023 accepted papers on Image generation

85 of the 2,023 papers accepted at AAAI 2023 (4.2%) are on Image generation, compared with 3.7% at AAAI 2022. They fall into 6 topics.

See AAAI 2023 in the interactive map

Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.

Topics and papers

Autoregressive and latent generation · 24 papers

Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation (109 citations)
Data-Efficient Image Quality Assessment with Attention-Panel Decoder (87 citations)
MDM: Molecular Diffusion Model for 3D Molecule Generation (81 citations)
Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis (65 citations)
Taxonomizing and Measuring Representational Harms: A Look at Image Tagging (28 citations)
A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech (27 citations)
GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps (19 citations)
Human-Instructed Deep Hierarchical Generative Learning for Automated Urban Planning (19 citations)
The Value of AI Guidance in Human Examination of Synthetically-Generated Faces (17 citations)
DENet: Disentangled Embedding Network for Visible Watermark Removal (16 citations)
UniSyn: An End-to-End Unified Model for Text-to-Speech and Singing Voice Synthesis (8 citations)
AutoStegaFont: Synthesizing Vector Fonts for Hiding Information in Documents (7 citations)

and 12 more in the interactive map.

Image restoration · 24 papers

Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method (523 citations)
Intriguing Findings of Frequency Selection for Image Deblurring (206 citations)
Underwater Ranker: Learn Which Is Better and How to Be Better (200 citations)
Hybrid CNN-Transformer Feature Fusion for Single Image Deraining (79 citations)
CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying (64 citations)
Dual-Domain Attention for Image Deblurring (56 citations)
Adaptive Dynamic Filtering Network for Image Denoising (55 citations)
Polarization-Aware Low-Light Image Enhancement (33 citations)
Robust Image Steganography: Hiding Messages in Frequency Coefficients (32 citations)
Estimating Reflectance Layer from a Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning (31 citations)
Painterly Image Harmonization in Dual Domains (24 citations)
Pixel-Wise Warping for Deep Image Stitching (23 citations)

and 12 more in the interactive map.

Editing and style transfer · 18 papers

MicroAST: Towards Super-fast Ultra-Resolution Arbitrary Style Transfer (55 citations)
Exploring Stroke-Level Modifications for Scene Text Editing (34 citations)
CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics (23 citations)
MIDMs: Matching Interleaved Diffusion Models for Exemplar-Based Image Translation (20 citations)
DE-net: Dynamic Text-Guided Image Editing Adversarial Networks (11 citations)
SHUNIT: Style Harmonization for Unpaired Image-to-Image Translation (9 citations)
CFFT-GAN: Cross-Domain Feature Fusion Transformer for Exemplar-Based Image Translation (8 citations)
SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines (8 citations)
ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing (7 citations)
AdaCM: Adaptive ColorMLP for Real-Time Universal Photo-Realistic Style Transfer (6 citations)
Mining and Applying Composition Knowledge of Dance Moves for Style-Concentrated Dance Generation (5 citations)
Multimodal Deep Generative Models for Remote Medical Applications (4 citations)

and 6 more in the interactive map.

Super-resolution · 9 papers

Hybrid Pixel-Unshuffled Network for Lightweight Image Super-resolution (85 citations)
SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting (51 citations)
GAN Prior Based Null-Space Learning for Consistent Super-resolution (42 citations)
Improving Scene Text Image Super-resolution via Dual Prior Modulation Network (38 citations)
From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-resolution (26 citations)
Gradient-Based Graph Attention for Scene Text Image Super-resolution (22 citations)
Recurrent Structure Attention Guidance for Depth Super-resolution (22 citations)
FSR: A General Frequency-Oriented Framework to Accelerate Image Super-resolution Networks (9 citations)
Structure Flow-Guided Network for Real Depth Super-resolution (9 citations)

GANs · 7 papers

Diffusion Models Beat GANs on Topology Optimization (72 citations)
Continuous Trajectory Generation Based on Two-Stage GAN (58 citations)
Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning (44 citations)
Avocodo: Generative Adversarial Network for Artifact-Free Vocoder (27 citations)
FEditNet: Few-Shot Editing of Latent Semantics in GAN Spaces (4 citations)
CoopInit: Initializing Generative Adversarial Networks via Cooperative Learning (2 citations)
IdProv: Identity-Based Provenance for Synthetic Image Generation (Student Abstract) (1 citation)