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 3 / 7 页

101. NeurIPS 2024EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
102. NeurIPS 2024EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models
103. NeurIPS 2024Exploring DCN-like architecture for fast image generation with arbitrary resolution
104. NeurIPS 2024Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models
105. NeurIPS 2024Face2QR: A Unified Framework for Aesthetic, Face-Preserving, and Scannable QR Code Generation
106. NeurIPS 2024Factorized Diffusion Architectures for Unsupervised Image Generation and Segmentation
107. NeurIPS 2024FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation
108. NeurIPS 2024FashionR2R: Texture-preserving Rendered-to-Real Image Translation with Diffusion Models
109. NeurIPS 2024Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time
110. NeurIPS 2024FastDrag: Manipulate Anything in One Step
111. NeurIPS 2024FIFO-Diffusion: Generating Infinite Videos from Text without Training
112. NeurIPS 2024FineStyle: Fine-grained Controllable Style Personalization for Text-to-image Models
113. NeurIPS 2024FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models
114. NeurIPS 2024FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributions
115. NeurIPS 2024FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner
116. NeurIPS 2024Fourier-enhanced Implicit Neural Fusion Network for Multispectral and Hyperspectral Image Fusion
117. NeurIPS 2024FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
118. NeurIPS 2024From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos
119. NeurIPS 2024From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
120. NeurIPS 2024From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
121. NeurIPS 2024FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference Images
122. NeurIPS 2024GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing
123. NeurIPS 2024Generalizable Person Re-identification via Balancing Alignment and Uniformity
124. NeurIPS 2024Generating compositional scenes via Text-to-image RGBA Instance Generation
125. NeurIPS 2024GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping
126. NeurIPS 2024GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation
127. NeurIPS 2024Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images
128. NeurIPS 2024Grasp as You Say: Language-guided Dexterous Grasp Generation
129. NeurIPS 2024GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation
130. NeurIPS 2024GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring
131. NeurIPS 2024GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
132. NeurIPS 2024Guiding a Diffusion Model with a Bad Version of Itself
133. NeurIPS 2024HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation
134. NeurIPS 2024Harmonizing Visual Text Comprehension and Generation
135. NeurIPS 2024HEST-1k: A Dataset For Spatial Transcriptomics and Histology Image Analysis
136. NeurIPS 2024HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation
137. NeurIPS 2024High-Resolution Image Harmonization with Adaptive-Interval Color Transformation
138. NeurIPS 2024Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation
139. NeurIPS 2024Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models
140. NeurIPS 2024How Control Information Influences Multilingual Text Image Generation and Editing?
141. NeurIPS 2024How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?
142. NeurIPS 2024HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
143. NeurIPS 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
144. NeurIPS 2024Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model
145. NeurIPS 2024Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models
146. NeurIPS 2024II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models
147. NeurIPS 2024Image Reconstruction Via Autoencoding Sequential Deep Image Prior
148. NeurIPS 2024Image Textualization: An Automatic Framework for Generating Rich and Detailed Image Descriptions
149. NeurIPS 2024Image Understanding Makes for A Good Tokenizer for Image Generation
150. NeurIPS 2024Image-aware Evaluation of Generated Medical Reports

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。