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 318 篇，第 2 / 7 页

51. NeurIPS 2024Conditional Controllable Image Fusion
52. NeurIPS 2024Conditional Synthesis of 3D Molecules with Time Correction Sampler
53. NeurIPS 2024Consistency Diffusion Bridge Models
54. NeurIPS 2024Constant Acceleration Flow
55. NeurIPS 2024Constrained Diffusion with Trust Sampling
56. NeurIPS 2024ContextCite: Attributing Model Generation to Context
57. NeurIPS 2024CosAE: Learnable Fourier Series for Image Restoration
58. NeurIPS 2024COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation
59. NeurIPS 2024Cross-Scale Self-Supervised Blind Image Deblurring via Implicit Neural Representation
60. NeurIPS 2024CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy
61. NeurIPS 2024Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance
62. NeurIPS 2024CV-VAE: A Compatible Video VAE for Latent Generative Video Models
63. NeurIPS 2024Data Attribution for Text-to-Image Models by Unlearning Synthesized Images
64. NeurIPS 2024DataComp-LM: In search of the next generation of training sets for language models
65. NeurIPS 2024DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor
66. NeurIPS 2024Dealing with Synthetic Data Contamination in Online Continual Learning
67. NeurIPS 2024DeBaRA: Denoising-Based 3D Room Arrangement Generation
68. NeurIPS 2024Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
69. NeurIPS 2024DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ
70. NeurIPS 2024DF40: Toward Next-Generation Deepfake Detection
71. NeurIPS 2024DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
72. NeurIPS 2024DiffuPac: Contextual Mimicry in Adversarial Packets Generation via Diffusion Model
73. NeurIPS 2024Diffusion Priors for Variational Likelihood Estimation and Image Denoising
74. NeurIPS 2024DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction
75. NeurIPS 2024DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation
76. NeurIPS 2024Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion models
77. NeurIPS 2024Direct Unlearning Optimization for Robust and Safe Text-to-Image Models
78. NeurIPS 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
79. NeurIPS 2024Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
80. NeurIPS 2024Discrete Modeling via Boundary Conditional Diffusion Processes
81. NeurIPS 2024Discrete-state Continuous-time Diffusion for Graph Generation
82. NeurIPS 2024Disentangled Style Domain for Implicit $z$-Watermark Towards Copyright Protection
83. NeurIPS 2024Diversify, Contextualize, and Adapt: Efficient Entropy Modeling for Neural Image Codec
84. NeurIPS 2024DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning
85. NeurIPS 2024Doubly Hierarchical Geometric Representations for Strand-based Human Hairstyle Generation
86. NeurIPS 2024DRACO: A Denoising-Reconstruction Autoencoder for Cryo-EM
87. NeurIPS 2024DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
88. NeurIPS 2024DRIP: Unleashing Diffusion Priors for Joint Foreground and Alpha Prediction in Image Matting
89. NeurIPS 2024EffiBench: Benchmarking the Efficiency of Automatically Generated Code
90. NeurIPS 2024Einsum Benchmark: Enabling the Development of Next-Generation Tensor Execution Engines
91. NeurIPS 2024ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis
92. NeurIPS 2024Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based Discrimination
93. NeurIPS 2024Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning
94. NeurIPS 2024EnsIR: An Ensemble Algorithm for Image Restoration via Gaussian Mixture Models
95. NeurIPS 2024Equivariant Neural Diffusion for Molecule Generation
96. NeurIPS 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention
97. NeurIPS 2024Evaluating alignment between humans and neural network representations in image-based learning tasks
98. NeurIPS 2024Evaluating Multiview Object Consistency in Humans and Image Models
99. NeurIPS 2024Evaluating Numerical Reasoning in Text-to-Image Models
100. NeurIPS 2024Evaluation of Text-to-Video Generation Models: A Dynamics Perspective

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。