AAAI 2024 accepted papers on Image generation
218 of the 2,864 papers accepted at AAAI 2024 (7.6%) are on Image generation, compared with 4.2% at AAAI 2023. They fall into 7 topics.
See AAAI 2024 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 · 44 papers
- DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection (70 citations)
- Transformer-Based No-Reference Image Quality Assessment via Supervised Contrastive Learning (45 citations)
- StegaStyleGAN: Towards Generic and Practical Generative Image Steganography (32 citations)
- UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding (27 citations)
- Decomposing Semantic Shifts for Composed Image Retrieval (23 citations)
- G2P-DDM: Generating Sign Pose Sequence from Gloss Sequence with Discrete Diffusion Model (22 citations)
- Learning to Rank in Generative Retrieval (21 citations)
- MuST: Robust Image Watermarking for Multi-Source Tracing (21 citations)
- VQ-FONT: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization (21 citations)
- R3CD: Scene Graph to Image Generation with Relation-Aware Compositional Contrastive Control Diffusion (15 citations)
- SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model (15 citations)
- DeepCalliFont: Few-Shot Chinese Calligraphy Font Synthesis by Integrating Dual-Modality Generative Models (14 citations)
and 32 more in the interactive map.
Editing and style transfer · 43 papers
- FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning (82 citations)
- ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank (63 citations)
- DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion (35 citations)
- Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style (28 citations)
- Towards Squeezing-Averse Virtual Try-On via Sequential Deformation (21 citations)
- AesFA: An Aesthetic Feature-Aware Arbitrary Neural Style Transfer (19 citations)
- Rethinking the Paradigm of Content Constraints in Unpaired Image-to-Image Translation (18 citations)
- TexFit: Text-Driven Fashion Image Editing with Diffusion Models (18 citations)
- A New Benchmark and Model for Challenging Image Manipulation Detection (17 citations)
- Controllable 3D Face Generation with Conditional Style Code Diffusion (16 citations)
- SyFormer: Structure-Guided Synergism Transformer for Large-Portion Image Inpainting (16 citations)
- ExpCLIP: Bridging Text and Facial Expressions via Semantic Alignment (14 citations)
and 31 more in the interactive map.
Image restoration · 36 papers
- Omni-Kernel Network for Image Restoration (275 citations)
- Correlation Matching Transformation Transformers for UHD Image Restoration (61 citations)
- Synergistic Multiscale Detail Refinement via Intrinsic Supervision for Underwater Image Enhancement (57 citations)
- Rethinking Multi-Scale Representations in Deep Deraining Transformer (47 citations)
- SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency (47 citations)
- Devignet: High-Resolution Vignetting Removal via a Dual Aggregated Fusion Transformer with Adaptive Channel Expansion (44 citations)
- Frequency-Adaptive Pan-Sharpening with Mixture of Experts (31 citations)
- VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook (30 citations)
- StegFormer: Rebuilding the Glory of Autoencoder-Based Steganography (27 citations)
- FMRNet: Image Deraining via Frequency Mutual Revision (24 citations)
- Underwater Organism Color Fine-Tuning via Decomposition and Guidance (23 citations)
- Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-Free Multi-Exposure Image Fusion (22 citations)
and 24 more in the interactive map.
Text-to-image diffusion · 36 papers
- T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion Models (865 citations)
- Constructing Dreams Using Generative AI (61 citations)
- IT3D: Improved Text-to-3D Generation with Explicit View Synthesis (52 citations)
- Directed Diffusion: Direct Control of Object Placement through Attention Guidance (40 citations)
- Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models (35 citations)
- DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models (29 citations)
- Text Image Inpainting via Global Structure-Guided Diffusion Models (29 citations)
- AltDiffusion: A Multilingual Text-to-Image Diffusion Model (26 citations)
- Audio Generation with Multiple Conditional Diffusion Model (26 citations)
- Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model (25 citations)
- Generating Images of Rare Concepts Using Pre-trained Diffusion Models (24 citations)
- A Picture Is Worth a Thousand Words: Co-designing Text-to-Image Generation Learning Materials for K-12 with Educators (22 citations)
and 24 more in the interactive map.
Fast diffusion sampling · 25 papers
- MedSegDiff-V2: Diffusion-Based Medical Image Segmentation with Transformer (263 citations)
- AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model (140 citations)
- Plug-In Diffusion Model for Sequential Recommendation (63 citations)
- Region-Disentangled Diffusion Model for High-Fidelity PPG-to-ECG Translation (39 citations)
- Enhancing Multi-Scale Diffusion Prediction via Sequential Hypergraphs and Adversarial Learning (28 citations)
- Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification (19 citations)
- MDFL: Multi-Domain Diffusion-Driven Feature Learning (18 citations)
- Controllable Mind Visual Diffusion Model (16 citations)
- CcDPM: A Continuous Conditional Diffusion Probabilistic Model for Inverse Design (12 citations)
- DiffSED: Sound Event Detection with Denoising Diffusion (10 citations)
- Multi-Architecture Multi-Expert Diffusion Models (10 citations)
- SPD-DDPM: Denoising Diffusion Probabilistic Models in the Symmetric Positive Definite Space (9 citations)
and 13 more in the interactive map.
Super-resolution · 23 papers
- ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (126 citations)
- OSFFNet: Omni-Stage Feature Fusion Network for Lightweight Image Super-Resolution (57 citations)
- SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-resolution (49 citations)
- S2CycleDiff: Spatial-Spectral-Bilateral Cycle-Diffusion Framework for Hyperspectral Image Super-resolution (21 citations)
- Enhancing Hyperspectral Images via Diffusion Model and Group-Autoencoder Super-resolution Network (20 citations)
- Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution (18 citations)
- Learning Multi-Modal Cross-Scale Deformable Transformer Network for Unregistered Hyperspectral Image Super-resolution (16 citations)
- Low-Light Face Super-resolution via Illumination, Structure, and Texture Associated Representation (16 citations)
- Transformer-Based Selective Super-resolution for Efficient Image Refinement (15 citations)
- Omnidirectional Image Super-resolution via Bi-projection Fusion (14 citations)
- SkipDiff: Adaptive Skip Diffusion Model for High-Fidelity Perceptual Image Super-resolution (14 citations)
- Uncertainty-Aware GAN for Single Image Super Resolution (14 citations)
and 11 more in the interactive map.
GANs · 11 papers
- RG-GAN: Dynamic Regenerative Pruning for Data-Efficient Generative Adversarial Networks (14 citations)
- Generative Model Perception Rectification Algorithm for Trade-Off between Diversity and Quality (12 citations)
- Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold (11 citations)
- Procedural Level Generation with Diffusion Models from a Single Example (9 citations)
- Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation (5 citations)
- Consistency-GAN: Training GANs with Consistency Model (4 citations)
- Spectrum Translation for Refinement of Image Generation (STIG) Based on Contrastive Learning and Spectral Filter Profile (4 citations)
- Discriminative Forests Improve Generative Diversity for Generative Adversarial Networks (3 citations)
- Neuroevolution of a Multi-Generator GAN (Student Abstract) (3 citations)
- Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks (3 citations)
- COPD-FlowNet: Elevating Non-invasive COPD Diagnosis with CFD Simulations (Student Abstract) (2 citations)