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 118 篇，第 2 / 3 页

51. ICLR 2023Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules
52. ICLR 2023InCoder: A Generative Model for Code Infilling and Synthesis
53. ICLR 2023Information-Theoretic Diffusion
54. ICLR 2023IS SYNTHETIC DATA FROM GENERATIVE MODELS READY FOR IMAGE RECOGNITION?
55. ICLR 2023ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation
56. ICLR 2023Iterative Circuit Repair Against Formal Specifications
57. ICLR 2023Kernel Neural Optimal Transport
58. ICLR 2023kNN-Diffusion: Image Generation via Large-Scale Retrieval
59. ICLR 2023Language Models Can Teach Themselves to Program Better
60. ICLR 2023Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations
61. ICLR 2023LDMIC: Learning-based Distributed Multi-view Image Coding
62. ICLR 2023Learning Input-agnostic Manipulation Directions in StyleGAN with Text Guidance
63. ICLR 2023Learning Iterative Neural Optimizers for Image Steganography
64. ICLR 2023Learning multi-scale local conditional probability models of images
65. ICLR 2023Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimization
66. ICLR 2023Learning to Generate Columns with Application to Vertex Coloring
67. ICLR 2023Learning with Stochastic Orders
68. ICLR 2023Linearly Mapping from Image to Text Space
69. ICLR 2023LPT: Long-tailed Prompt Tuning for Image Classification
70. ICLR 2023Make-A-Video: Text-to-Video Generation without Text-Video Data
71. ICLR 2023Markup-to-Image Diffusion Models with Scheduled Sampling
72. ICLR 2023Masked Image Modeling with Denoising Contrast
73. ICLR 2023Measuring axiomatic soundness of counterfactual image models
74. ICLR 2023Molecule Generation For Target Protein Binding with Structural Motifs
75. ICLR 2023Multi-domain image generation and translation with identifiability guarantees
76. ICLR 2023NERDS: A General Framework to Train Camera Denoisers from Raw-RGB Noisy Image Pairs
77. ICLR 2023Neural Groundplans: Persistent Neural Scene Representations from a Single Image
78. ICLR 2023Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modeling
79. ICLR 2023Neural Optimal Transport
80. ICLR 2023Non-parametric Outlier Synthesis
81. ICLR 2023Offline RL for Natural Language Generation with Implicit Language Q Learning
82. ICLR 2023On the Data-Efficiency with Contrastive Image Transformation in Reinforcement Learning
83. ICLR 2023On the Usefulness of Embeddings, Clusters and Strings for Text Generation Evaluation
84. ICLR 2023Out-of-Distribution Detection and Selective Generation for Conditional Language Models
85. ICLR 2023Outcome-directed Reinforcement Learning by Uncertainty \& Temporal Distance-Aware Curriculum Goal Generation
86. ICLR 2023PaLI: A Jointly-Scaled Multilingual Language-Image Model
87. ICLR 2023Phenaki: Variable Length Video Generation from Open Domain Textual Descriptions
88. ICLR 2023PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales
89. ICLR 2023Planning with Large Language Models for Code Generation
90. ICLR 2023Prompt-to-Prompt Image Editing with Cross-Attention Control
91. ICLR 2023PV3D: A 3D Generative Model for Portrait Video Generation
92. ICLR 2023Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images
93. ICLR 2023Re-Imagen: Retrieval-Augmented Text-to-Image Generator
94. ICLR 2023Real-Time Image Demoir$\acute{e}$ing on Mobile Devices
95. ICLR 2023Red PANDA: Disambiguating Image Anomaly Detection by Removing Nuisance Factors
96. ICLR 2023Rethinking skip connection model as a learnable Markov chain
97. ICLR 2023Scalable Subset Sampling with Neural Conditional Poisson Networks
98. ICLR 2023Scaling Laws For Deep Learning Based Image Reconstruction
99. ICLR 2023Schema Inference for Interpretable Image Classification
100. ICLR 2023Selective Frequency Network for Image Restoration

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。