CVPR 2026 accepted papers on Image generation
598 of the 4,042 papers accepted at CVPR 2026 (14.8%) are on Image generation, compared with 16.8% at CVPR 2025. They fall into 7 topics.
See CVPR 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
Text-to-image diffusion · 182 papers
- TokenTrace: Multi-Concept Attribution through Watermarked Token Recovery (1 citation)
- A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space
- AceTone: Bridging Words and Colors for Conditional Image Grading
- Adapter Shield: A Unified Framework with Built-in Authentication for Preventing Unauthorized Zero-Shot Image-to-Image Generation
- Adaptive Auxiliary Prompt Blending for Target-Faithful Diffusion Generation
- Agentic Retoucher for Text-To-Image Generation
- Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation
- Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models
- Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation
- Beyond Pixel Simulation: Pathology Image Generation via Diagnostic Semantic Tokens and Prototype Control
- Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
- Bias at the End of the Score
and 170 more in the interactive map.
Autoregressive and latent generation · 122 papers
- A Difference-in-Difference Approach to Detecting AI-Generated Images
- ACPV-Net: All-Class Polygonal Vectorization for Seamless Vector Map Generation from Aerial Imagery
- Anatomica: Localized Control over Geometric and Topological Properties for Anatomical Diffusion Models
- Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution
- CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization
- Cell-Type Prototype-Informed Neural Network for Gene Expression Estimation from Pathology Images
- CG-Floor: Centroid-Guided Diffusion for Large-Scale Floorplan Generation
- ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clustering
- Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens
- DA-VAE: Plug-in Latent Compression for Diffusion via Detail Alignment
- DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
- Detecting AI-Generated Forgeries via Iterative Manifold Deviation Amplification
and 110 more in the interactive map.
Fast diffusion sampling · 101 papers
- Back to Basics: Let Denoising Generative Models Denoise (4 citations)
- Understanding, Accelerating, and Improving MeanFlow Training (1 citation)
- 2ndMatch: Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching
- Accelerating Diffusion Model Training under Minimal Budgets: A Condensation-Based Perspective
- Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling
- Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression Generation from Histology Images
- Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration
- Advancing Image Classification with Discrete Diffusion Classification Modeling
- Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models
- BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation
- BiGain: Unified Token Compression for Joint Generation and Classification
- CaricHarmony: Contrastive Diffusion Paths for Identity-Preserving Caricature Synthesis
and 89 more in the interactive map.
Image restoration · 79 papers
- cryoSENSE: Compressive Sensing Enables High-throughput Microscopy with Sparse and Generative Priors on the Protein Cryo-EM Image Manifold (1 citation)
- 2-Shots in the Dark: Low-Light Denoising with Minimal Data Acquisition
- Benchmarking Endoscopic Surgical Image Restoration and Beyond
- Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration
- BiEvLight: Bi-level Learning of Task-Aware Event Refinement for Low-Light Image Enhancement
- BluRef: Unsupervised Image Deblurring with Dense-Matching References
- CADC: Content Adaptive Diffusion-Based Generative Image Compression
- CARD: Correlation Aware Restoration with Diffusion
- Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark
- Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios
- Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning
- Distributed Image Compression with Multimodal Side Information at Extremely Low Bitrates
and 67 more in the interactive map.
Editing and style transfer · 74 papers
- Precise Object and Effect Removal with Adaptive Target-Aware Attention (1 citation)
- A Training-Free Style-Personalization via SVD-Based Feature Decomposition
- AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows
- CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing
- ChordEdit: One-Step Low-Energy Transport for Image Editing
- Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization
- CogniEdit: Dense Gradient Flow Optimization for Fine-Grained Image Editing
- ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorization
- CompBench: Benchmarking Complex Instruction-guided Image Editing
- Cycle-Consistent Tuning for Layered Image Decomposition
- Delta Rectified Flow Sampling for Text-to-Image Editing
- DiffDecompose: Layer-Wise Decomposition of Alpha-Composited Images via Diffusion Transformers
and 62 more in the interactive map.
Super-resolution · 39 papers
- 3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusion
- Beyond the Ground Truth: Enhanced Supervision for Image Restoration
- Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution
- CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awareness
- Disentangled Textual Priors for Diffusion-based Image Super-Resolution
- DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution
- DreamSR: Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion Transformer
- DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution
- Enhancing Unregistered Hyperspectral Image Super-Resolution via Unmixing-based Abundance Fusion Learning
- FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution
- FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution
- FRAMER: Frequency-Aligned Self-Distillation with Adaptive Modulation Leveraging Diffusion Priors for Real-World Image Super-Resolution
and 27 more in the interactive map.