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 944 篇，第 2 / 19 页

51. ICLR 2026CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation
52. ICLR 2026Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss
53. ICLR 2026Condition Matters in Full-head 3D GANs
54. ICLR 2026CONSIGN: Conformal Segmentation Informed by Spatial Groupings via Decomposition
55. ICLR 2026Consistent Text-to-Image Generation via Scene De-Contextualization
56. ICLR 2026Constantly Improving Image Models Need Constantly Improving Benchmarks
57. ICLR 2026Constrained Decoding of Diffusion LLMs with Context-Free Grammars
58. ICLR 2026ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation
59. ICLR 2026Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective
60. ICLR 2026Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling
61. ICLR 2026Controllable diffusion-based generation for multi-channel biological data
62. ICLR 2026Controllable Video Generation with Provable Disentanglement
63. ICLR 2026CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design
64. ICLR 2026CroCoDiLight: Repurposing Cross-View Completion Encoders for Relighting
65. ICLR 2026Cross-ControlNet: Training-Free Fusion of Multiple Conditions for Text-to-Image Generation
66. ICLR 2026CrossPL: Systematic Evaluation of Large Language Models for Cross Programming Language Interoperating Code Generation
67. ICLR 2026Culture in Action: Evaluating Text-to-Image Models through Social Activities
68. ICLR 2026D-AR: Diffusion via Autoregressive Models
69. ICLR 2026DanceTogether: Generating Interactive Multi-Person Video without Identity Drifting
70. ICLR 2026Data Provenance for Image Auto-Regressive Generation
71. ICLR 2026DCFold: Efficient Protein Structure Generation with Single Forward Pass
72. ICLR 2026Deconstructing Guidance: A Semantic Hierarchy for Precise Diffusion Model Editing
73. ICLR 2026DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models
74. ICLR 2026Detective SAM: Adaptive AI-Image Forgery Localization
75. ICLR 2026DiffInk: Glyph- and Style-Aware Latent Diffusion Transformer for Text to Online Handwriting Generation
76. ICLR 2026Diffusion Negative Preference Optimization Made Simple
77. ICLR 2026DiMeR: Disentangled Mesh Reconstruction Model with Normal-only Geometry Training
78. ICLR 2026Directional Textual Inversion for Personalized Text-to-Image Generation
79. ICLR 2026Discrete Bayesian Sample Inference for Graph Generation
80. ICLR 2026Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation
81. ICLR 2026DistillKac: Few-Step Image Generation via Damped Wave Equations
82. ICLR 2026Distributional Consistency Loss: Beyond Pointwise Data Terms in Inverse Problems
83. ICLR 2026Divergence-Free Neural Networks with Application to Image Denoising
84. ICLR 2026Diverse Text Decoding via Iterative Reweighting
85. ICLR 2026Diverse Text-to-Image Generation via Contrastive Noise Optimization
86. ICLR 2026Do We Need All the Synthetic Data? Targeted Image Augmentation via Diffusion Models
87. ICLR 2026Dragging with Geometry: From Pixels to Geometry-Guided Image Editing
88. ICLR 2026Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing
89. ICLR 2026DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision
90. ICLR 2026Dual-Kernel Adapter: Expanding Spatial Horizons for Data-Constrained Medical Image Analysis
91. ICLR 2026Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer
92. ICLR 2026Dynamic Classifier-Free Diffusion Guidance via Online Feedback
93. ICLR 2026Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
94. ICLR 2026EchoGen: Generating Visual Echoes in Any Scene via Feed-Forward Subject-Driven Auto-Regressive Model
95. ICLR 2026EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
96. ICLR 2026ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM Framework
97. ICLR 2026Energy-Efficient Random Variate Generation via Compressed Lookup Tables
98. ICLR 2026Enhancing Image-Conditional Coverage in Segmentation: Adaptive Thresholding via Differentiable Miscoverage Loss
99. ICLR 2026Enhancing Multi-Image Understanding through Delimiter Token Scaling
100. ICLR 2026Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints

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。