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 612 篇，第 2 / 13 页

51. CVPR 2025Autoregressive Distillation of Diffusion Transformers
52. CVPR 2025BACON: Improving Clarity of Image Captions via Bag-of-Concept Graphs
53. CVPR 2025BADGR: Bundle Adjustment Diffusion Conditioned by Gradients for Wide-Baseline Floor Plan Reconstruction
54. CVPR 2025Balanced Rate-Distortion Optimization in Learned Image Compression
55. CVPR 2025Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning
56. CVPR 2025beta-FFT: Nonlinear Interpolation and Differentiated Training Strategies for Semi-Supervised Medical Image Segmentation
57. CVPR 2025Beyond Generation: A Diffusion-based Low-level Feature Extractor for Detecting AI-generated Images
58. CVPR 2025Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt Learning
59. CVPR 2025Binarized Neural Network for Multi-spectral Image Fusion
60. CVPR 2025BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature
61. CVPR 2025BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation
62. CVPR 2025Black Hole-Driven Identity Absorbing in Diffusion Models
63. CVPR 2025BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations
64. CVPR 2025BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers
65. CVPR 2025Boltzmann Attention Sampling for Image Analysis with Small Objects
66. CVPR 2025Boost Your Human Image Generation Model via Direct Preference Optimization
67. CVPR 2025BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training
68. CVPR 2025BrepGiff: Lightweight Generation of Complex B-rep with 3D GAT Diffusion
69. CVPR 2025Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression
70. CVPR 2025ByTheWay: Boost Your Text-to-Video Generation Model to Higher Quality in a Training-free Way
71. CVPR 2025CacheQuant: Comprehensively Accelerated Diffusion Models
72. CVPR 2025CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generation
73. CVPR 2025CADDreamer: CAD Object Generation from Single-view Images
74. CVPR 2025CamFreeDiff: Camera-free Image to Panorama Generation with Diffusion Model
75. CVPR 2025Can Text-to-Video Generation help Video-Language Alignment?
76. CVPR 2025CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image
77. CVPR 2025CaricatureBooth: Data-Free Interactive Caricature Generation in a Photo Booth
78. CVPR 2025CARL: A Framework for Equivariant Image Registration
79. CVPR 2025CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution
80. CVPR 2025Causal Composition Diffusion Model for Closed-loop Traffic Generation
81. CVPR 2025CCIN: Compositional Conflict Identification and Neutralization for Composed Image Retrieval
82. CVPR 2025Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining
83. CVPR 2025Charm: The Missing Piece in ViT Fine-Tuning for Image Aesthetic Assessment
84. CVPR 2025Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models
85. CVPR 2025ChatGarment: Garment Estimation, Generation and Editing via Large Language Models
86. CVPR 2025ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting
87. CVPR 2025CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning
88. CVPR 2025Classifier-Free Guidance Inside the Attraction Basin May Cause Memorization
89. CVPR 2025CoA: Towards Real Image Dehazing via Compression-and-Adaptation
90. CVPR 2025CoLLM: A Large Language Model for Composed Image Retrieval
91. CVPR 2025Color Alignment in Diffusion
92. CVPR 2025CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation
93. CVPR 2025Community Forensics: Using Thousands of Generators to Train Fake Image Detectors
94. CVPR 2025Compass Control: Multi Object Orientation Control for Text-to-Image Generation
95. CVPR 2025CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians
96. CVPR 2025Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising
97. CVPR 2025Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion
98. CVPR 2025Complexity Experts are Task-Discriminative Learners for Any Image Restoration
99. CVPR 2025Composing Parts for Expressive Object Generation
100. CVPR 2025Concept Lancet: Image Editing with Compositional Representation Transplant

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。