AAAI 2026 accepted papers on Image generation
342 of the 4,417 papers accepted at AAAI 2026 (7.7%) are on Image generation, compared with 8.3% at AAAI 2025. They fall into 7 topics.
See AAAI 2026 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 · 90 papers
- IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech (6 citations)
- GenPTW: Latent Image Watermarking for Provenance Tracing and Tamper Localization (4 citations)
- PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancement (3 citations)
- Zooming In on Fakes: A Novel Dataset for Localized AI-Generated Image Detection with Forgery Amplification Approach (3 citations)
- AEDR: Training-Free AI-Generated Image Attribution via Autoencoder Double-Reconstruction (2 citations)
- Explainable Synthetic Image Detection Through Diffusion Timestep Ensembling (2 citations)
- Fine-grained Image Quality Assessment for Perceptual Image Restoration (2 citations)
- Mitigating Perception Bias: A Training-Free Approach to Enhance LMM for Image Quality Assessment (2 citations)
- Virtual Multiplex Staining for Histological Images Using a Marker-Wise Conditioned Diffusion Model (2 citations)
- Beyond Adapter Retrieval: Latent Geometry-Preserving Composition via Sparse Task Projection (1 citation)
- CoCoLIT: ControlNet-Conditioned Latent Image Translation for MRI to Amyloid PET Synthesis (1 citation)
- CondDiff-AMO: Integrating Conditional Diffusion Mechanism for Unified Amodal Mask Generation (1 citation)
and 78 more in the interactive map.
Text-to-image diffusion · 74 papers
- VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation (6 citations)
- EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering (4 citations)
- EvalMuse-40K: A Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Alignment Evaluation (3 citations)
- Personalize Anything for Free with Diffusion Transformer (3 citations)
- Talk2Image: A Multi-Agent System for Multi-Turn Image Generation and Editing (3 citations)
- GuideGen: A Text-Guided Framework for Paired Full-torso Anatomy and CT Volume Generation (2 citations)
- Margin-Aware Preference Optimization for Aligning Diffusion Models Without Reference (2 citations)
- Any2RSI: Controllable Remote Sensing Text-to-Image Generation via Any Control and Enriched Description (1 citation)
- DOS: Directional Object Separation in Text Embeddings for Multi-Object Image Generation (1 citation)
- FreeInpaint: Tuning-free Prompt Alignment and Visual Rationality Enhancement in Image Inpainting (1 citation)
- Infinite-Story: A Training-Free Consistent Text-to-Image Generation (1 citation)
- LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer (1 citation)
and 62 more in the interactive map.
Image restoration · 62 papers
- Pansharpening for Thin-Cloud Contaminated Remote Sensing Images: A Unified Framework and Benchmark Dataset (14 citations)
- MAISI-v2: Accelerated 3D High-Resolution Medical Image Synthesis with Rectified Flow and Region-specific Contrastive Loss (9 citations)
- ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration (4 citations)
- SPJFNet: Self-Mining Prior-Guided Joint Frequency Enhancement for Ultra-Efficient Dark Image Restoration (4 citations)
- Dereflection Any Image with Diffusion Priors and Diversified Data (3 citations)
- Diffusion Once and Done: Degradation-Aware LoRA for All-in-One Image Restoration (3 citations)
- Polarization Uncertainty-Guided Diffusion Model for Color Polarization Image Demosaicking (3 citations)
- Bayesian Neural Networks for One-to-Many Mapping in Image Enhancement (2 citations)
- Beyond Illumination: Fine-Grained Detail Preservation in Extreme Dark Image Restoration (2 citations)
- Conditional Prompt Learning via Degradation Perception for Underwater Image Enhancement (2 citations)
- EndoIR: Degradation-Agnostic All-in-One Endoscopic Image Restoration via Noise-Aware Routing Diffusion (2 citations)
- Gradient as Conditions: Rethinking HOG for All-in-one Image Restoration (2 citations)
and 50 more in the interactive map.
Fast diffusion sampling · 61 papers
- Rectified Noise: A Generative Model Using Positive-incentive Noise (4 citations)
- Forecast Then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers (3 citations)
- SAR-DisentDM: A Semantic-Disentangled Diffusion Model for Limited-Data SAR Image Synthesis (3 citations)
- Directing Uncertainty-Aware Information Flow for Robust Diffusion Prediction (2 citations)
- MP1: MeanFlow Tames Policy Learning in 1-step for Robotic Manipulation (2 citations)
- Spatial-Temporal Feedback Diffusion Guidance for Controlled Traffic Imputation (2 citations)
- Constrained Particle Seeking: Solving Diffusion Inverse Problems with Just Forward Passes (1 citation)
- D3ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs (1 citation)
- De-collapsing User Intent: Adaptive Diffusion Augmentation with Mixture-of-Experts for Sequential Recommendation (1 citation)
- DiffMM: Efficient Method for Accurate Noisy and Sparse Trajectory Map Matching via One Step Diffusion (1 citation)
- Diffusion Distillation with Direct Preference Optimization for Efficient 3D LiDAR Scene Completion (1 citation)
- Discrete-Guided Diffusion for Scalable and Safe Multi-Robot Motion Planning (1 citation)
and 49 more in the interactive map.
Editing and style transfer · 35 papers
- Insert Anything: Image Insertion via In-Context Editing in DiT (8 citations)
- X2Edit: Revisiting Arbitrary-Instruction Image Editing Through Self-Constructed Data and Task-Aware Representation Learning (3 citations)
- An Efficient and Harmonized Framework for Balanced Cross-Domain Feature Integration (2 citations)
- Cognitive Enhancement Chain-of-Thought Towards Enhancing Style Learning and Content Preservation for Long Style Transfer (2 citations)
- DragNeXt: Rethinking Drag-Based Image Editing (2 citations)
- FIA-Edit: Frequency-Interactive Attention for Efficient and High-Fidelity Inversion-Free Text-Guided Image Editing (2 citations)
- Gracefully Air-Written: Enhancing the Legibility and Style Consistency of In-Air Handwriting (2 citations)
- MCIE: Multimodal LLM-Driven Complex Instruction Image Editing with Spatial Guidance (2 citations)
- TweezeEdit: Consistent and Efficient Image Editing with Path Regularization (2 citations)
- ACID-Style: An Adaptive Condition Injection Diffusion Model for Arbitrary Style Transfer (1 citation)
- Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing (1 citation)
- BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching (1 citation)
and 23 more in the interactive map.
Super-resolution · 17 papers
- MFmamba: A Multi-function Network for Panchromatic Image Resolution Restoration Based on State-Space Model (3 citations)
- Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion Guidance (3 citations)
- PortraitSR: Artist-Inspired Prior Learning for Progressive Face Super-Resolution (2 citations)
- CD-DPE: Dual-Prompt Expert Network Based on Convolutional Dictionary Feature Decoupling for Multi-Contrast MRI Super-Resolution (1 citation)
- Inference-time Scaling for Diffusion-based Audio Super-resolution (1 citation)
- Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution (1 citation)
- Realism Control One-step Diffusion for Real-world Image Super Resolution (1 citation)
- TRT: Harnessing Tensor Ring Transformer for Hyperspectral Image Super-Resolution (1 citation)
- Burst Image Quality Assessment: A New Benchmark and Unified Framework for Multiple Downstream Tasks
- Continuous Degradation Modeling via Latent Flow Matching for Real-World Super-Resolution
- Event-Guided Scene Text Image Super-Resolution
- Event-Guided Super-Resolving Blurry Image via Asymmetric Integral Driven Consistency
and 5 more in the interactive map.