图像生成论文趋势 2023–2026

主要结论

• 图像生成论文从 2023 年的 780 篇增长到 2026 年的 1,721 篇，三年间扩大到约 2.2 倍。
• CVPR 是发图像生成论文最多的会议，2023–2026 年共 2,262 篇，占四个会议总量的 44%。
• 交叉方向里涨得最快的是深度学习 · generative models and autoencoders：同时属于两个主题的论文从 2023 年的 35 篇增至 2026 年的 150 篇。
• 在「计算机视觉」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的视频理解是 2.6 倍，图像生成是 2.2 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026$\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
• ICML 2026Klein Hyperbolic Metric Learning
• ICLR 2026A Bayesian Nonparametric Framework for Private, Fair, and Balanced Tabular Data Synthesis
• CVPR 2026Adaptive Learned Image Compression with Graph Neural Networks
• NeurIPS 2025Alchemist: Turning Public Text-to-Image Data into Generative Gold
• ICML 2025BiMark: Unbiased Multilayer Watermarking for Large Language Models
• ICLR 2025Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
• CVPR 2025A Polarization-Aided Transformer for Image Deblurring via Motion Vector Decomposition
• NeurIPS 2024Einsum Benchmark: Enabling the Development of Next-Generation Tensor Execution Engines
• ICML 2024Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity
• ICLR 2024AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ
• CVPR 2024DemoCaricature: Democratising Caricature Generation with a Rough Sketch
• NeurIPS 20234D Panoptic Scene Graph Generation
• ICML 2023Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN
• ICLR 2023Accurate Image Restoration with Attention Retractable Transformer
• CVPR 20233D GAN Inversion With Facial Symmetry Prior
• NeurIPS 2026A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
• ICML 2026Noisy-Channel Minimum Bayes Risk Decoding
• ICLR 2026All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning
• CVPR 2026AIMDepth Asymmetric Image-Event Mamba for Monocular Depth Estimation

全部图像生成论文

共 689 篇，第 2 / 14 页

51. CVPR 2026Bidirectional Query-Driven Generation of Parametric CAD Sketch
52. CVPR 2026BiEvLight Bi-level Learning of Task-Aware Event Refinement for Low-Light Image
53. CVPR 2026BiFM Bidirectional Flow Matching for Few-Step Image Editing and Generation
54. CVPR 2026BiGain Unified Token Compression for Joint Generation and Classification
55. CVPR 2026Bilevel Layer-Positioning LoRA for Real Image Dehazing
56. CVPR 2026BiMotion B-spline Motion for Text-guided Dynamic 3D Character Generation
57. CVPR 2026Black-box Membership Inference Attacks on the Pre-training Data of Image-generation
58. CVPR 2026BlackMirror Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation
59. CVPR 2026Block-based Learned Image Compression without Blocking Artifacts
60. CVPR 2026BluRef Unsupervised Image Deblurring with Dense-Matching References
61. CVPR 2026Breaking Semantic Boundaries Distribution-Guided Semantic Exploration for Creative Generation
62. CVPR 2026Breaking the 3D Dataset Bottleneck Fast Scalable Generation of Aligned
63. CVPR 2026Breaking the Illusion When Positive Meets Negative in Multimodal Decoding
64. CVPR 2026Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution
65. CVPR 2026Bridging Human Evaluation to Infrared and Visible Image Fusion
66. CVPR 2026Bridging Privacy and Provenance Traceable Virtual Identity Generation
67. CVPR 2026Bridging the Modality Gap in Compositional Zero-Shot Learning via Sparse
68. CVPR 2026Bridging the Perception Gap in Image Super-Resolution Evaluation
69. CVPR 2026Bringing Your Portrait to 3D Presence
70. CVPR 2026C-GenReg Training-Free 3D Point Cloud Registration by Multi-View-Consistent Geometry-to-Image Generation
71. CVPR 2026CAD-Refiner A Unified Framework for CAD Generation and Iterative Editing
72. CVPR 2026CADC Content Adaptive Diffusion-Based Generative Image Compression
73. CVPR 2026CaliTex Geometry-Calibrated Attention for View-Coherent 3D Texture Generation
74. CVPR 2026Camera Control for Text-to-Image Generation via Learning Viewpoint Tokens
75. CVPR 2026Camouflage-aware Image-Text Retrieval via Expert Collaboration
76. CVPR 2026Can a Second-View Image Be a Language Geometric and Semantic
77. CVPR 2026Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range
78. CVPR 2026Can We Build Scene Graphs Not Classify Them FlowSG Progressive
79. CVPR 2026CaptionQA Is Your Caption as Useful as the Image Itself
80. CVPR 2026CARE-Edit Condition-Aware Routing of Experts for Contextual Image Editing
81. CVPR 2026CAST Context-Aware Dynamic Latent Space Transformation for Interactive Text-to-Image Retrieval
82. CVPR 2026CaTok Taming Mean Flows for One-Dimensional Causal Image Tokenization
83. CVPR 2026Causal Motion Diffusion Models for Autoregressive Motion Generation
84. CVPR 2026CCCaption Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning
85. CVPR 2026CFG-Ctrl Control-Based Classifier-Free Diffusion Guidance
86. CVPR 2026ChangeBridge Spatiotemporal Image Generation with Multimodal Controls for Remote Senisng
87. CVPR 2026Charge A Comprehensive Novel View Synthesis Benchmark and Dataset to
88. CVPR 2026ChordEdit One-Step Low-Energy Transport for Image Editing
89. CVPR 2026Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers
90. CVPR 2026ClusterMark Towards Robust Watermarking for Autoregressive Image Generators with Visual
91. CVPR 2026CoD A Diffusion Foundation Model for Image Compression
92. CVPR 2026CodeMMR Bridging Natural Language Code and Image for Unified Retrieval
93. CVPR 2026CogniEdit Dense Gradient Flow Optimization for Fine-Grained Image Editing
94. CVPR 2026CogniVerse Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric
95. CVPR 2026CoLoGen Progressive Learning of Concept-Localization Duality for Unified Image Generation
96. CVPR 2026CompBench Benchmarking Complex Instruction-guided Image Editing
97. CVPR 2026Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization
98. CVPR 2026Concept-Aware Batch Sampling Improves Language-Image Pretraining
99. CVPR 2026Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generation
100. CVPR 2026ConceptPrism Concept Disentanglement in Personalized Diffusion Models via Residual Token

常见问题

2023–2026 年四大会议一共有多少篇图像生成论文？

共 5,184 篇，按年份分别是 2023 年 780 篇、2024 年 1,216 篇、2025 年 1,467 篇、2026 年 1,721 篇。

NeurIPS 2026 有多少篇图像生成论文？

NeurIPS 2026 有 453 篇图像生成论文，上一届是 430 篇。

ICLR 2026 有多少篇图像生成论文？

ICLR 2026 有 349 篇图像生成论文，上一届是 278 篇。

ICML 2026 有多少篇图像生成论文？

ICML 2026 有 230 篇图像生成论文，上一届是 147 篇。

CVPR 2026 有多少篇图像生成论文？

CVPR 2026 有 689 篇图像生成论文，上一届是 612 篇。

哪个会议的图像生成论文最多？

CVPR，2023–2026 年共 2,262 篇。