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 278 篇，第 3 / 6 页

101. ICLR 2025Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective
102. ICLR 2025Exploiting Distribution Constraints for Scalable and Efficient Image Retrieval
103. ICLR 2025FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models
104. ICLR 2025Fantastic Copyrighted Beasts and How (Not) to Generate Them
105. ICLR 2025Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation
106. ICLR 2025FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models
107. ICLR 2025Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens
108. ICLR 2025Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
109. ICLR 2025Forking Paths in Neural Text Generation
110. ICLR 2025FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling
111. ICLR 2025Fréchet Wavelet Distance: A Domain-Agnostic Metric for Image Generation
112. ICLR 2025Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs
113. ICLR 2025FreeVS: Generative View Synthesis on Free Driving Trajectory
114. ICLR 2025From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities
115. ICLR 2025GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation
116. ICLR 2025GaussianAnything: Interactive Point Cloud Flow Matching for 3D Generation
117. ICLR 2025GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time Alignment
118. ICLR 2025Generalizable Human Gaussians from Single-View Image
119. ICLR 2025Generalized Consistency Trajectory Models for Image Manipulation
120. ICLR 2025Generation and Comprehension Hand-in-Hand: Vision-guided Expression Diffusion for Boosting Referring Expression Generation and Comprehension
121. ICLR 2025Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation
122. ICLR 2025GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation
123. ICLR 2025Glad: A Streaming Scene Generator for Autonomous Driving
124. ICLR 2025GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation
125. ICLR 2025Gradient-Free Generation for Hard-Constrained Systems
126. ICLR 2025Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion Models
127. ICLR 2025Guaranteed Generation from Large Language Models
128. ICLR 2025Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation
129. ICLR 2025Gumbel Counterfactual Generation From Language Models
130. ICLR 2025Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation
131. ICLR 2025Halton Scheduler for Masked Generative Image Transformer
132. ICLR 2025HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
133. ICLR 2025HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models
134. ICLR 2025HGM³: Hierarchical Generative Masked Motion Modeling with Hard Token Mining
135. ICLR 2025High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity
136. ICLR 2025High-Quality Joint Image and Video Tokenization with Causal VAE
137. ICLR 2025High-quality Text-to-3D Character Generation with SparseCubes and Sparse Transformers.
138. ICLR 2025How Much is a Noisy Image Worth? Data Scaling Laws for Ambient Diffusion.
139. ICLR 2025Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment
140. ICLR 2025Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation
141. ICLR 2025HyperPLR: Hypergraph Generation through Projection, Learning, and Reconstruction
142. ICLR 2025Image and Video Tokenization with Binary Spherical Quantization
143. ICLR 2025Image Watermarks are Removable using Controllable Regeneration from Clean Noise
144. ICLR 2025Image-level Memorization Detection via Inversion-based Inference Perturbation
145. ICLR 2025ImageFolder: Autoregressive Image Generation with Folded Tokens
146. ICLR 2025Improving Long-Text Alignment for Text-to-Image Diffusion Models
147. ICLR 2025Improving Neural Optimal Transport via Displacement Interpolation
148. ICLR 2025Improving Uncertainty Estimation through Semantically Diverse Language Generation
149. ICLR 2025InCoDe: Interpretable Compressed Descriptions For Image Generation
150. ICLR 2025Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On

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。