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 1 / 7 页

1. NeurIPS 2024$\textit{Bifr\"ost}$: 3D-Aware Image Compositing with Language Instructions
2. NeurIPS 20242DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
3. NeurIPS 2024A Cat Is A Cat (Not A Dog!): Unraveling Information Mix-ups in Text-to-Image Encoders through Causal Analysis and Embedding Optimization
4. NeurIPS 2024A Modular Conditional Diffusion Framework for Image Reconstruction
5. NeurIPS 2024A Simple Image Segmentation Framework via In-Context Examples
6. NeurIPS 2024A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation
7. NeurIPS 2024ActAnywhere: Subject-Aware Video Background Generation
8. NeurIPS 2024Action Imitation in Common Action Space for Customized Action Image Synthesis
9. NeurIPS 2024Adaptable Logical Control for Large Language Models
10. NeurIPS 2024Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis
11. NeurIPS 2024Adaptive Domain Learning for Cross-domain Image Denoising
12. NeurIPS 2024Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare
13. NeurIPS 2024Adaptive Visual Scene Understanding: Incremental Scene Graph Generation
14. NeurIPS 2024AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection
15. NeurIPS 2024Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generation
16. NeurIPS 2024Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation
17. NeurIPS 2024AID: Attention Interpolation of Text-to-Image Diffusion
18. NeurIPS 2024Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization
19. NeurIPS 2024An Image is Worth 32 Tokens for Reconstruction and Generation
20. NeurIPS 2024AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion Models
21. NeurIPS 2024APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets
22. NeurIPS 2024Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting
23. NeurIPS 2024ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users
24. NeurIPS 2024AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
25. NeurIPS 2024Ask, Attend, Attack: An Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models
26. NeurIPS 2024Association of Objects May Engender Stereotypes: Mitigating Association-Engendered Stereotypes in Text-to-Image Generation
27. NeurIPS 2024Attack-Resilient Image Watermarking Using Stable Diffusion
28. NeurIPS 2024AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation
29. NeurIPS 2024Autoregressive Image Diffusion: Generation of Image Sequence and Application in MRI
30. NeurIPS 2024Autoregressive Image Generation without Vector Quantization
31. NeurIPS 2024Benchmarking Counterfactual Image Generation
32. NeurIPS 2024Beyond Aesthetics: Cultural Competence in Text-to-Image Models
33. NeurIPS 2024Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency
34. NeurIPS 2024Binarized Diffusion Model for Image Super-Resolution
35. NeurIPS 2024BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity
36. NeurIPS 2024BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
37. NeurIPS 2024BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval
38. NeurIPS 2024Blind Image Restoration via Fast Diffusion Inversion
39. NeurIPS 2024Boosting Alignment for Post-Unlearning Text-to-Image Generative Models
40. NeurIPS 2024Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation
41. NeurIPS 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Models
42. NeurIPS 2024Categorical Flow Matching on Statistical Manifolds
43. NeurIPS 2024Causal Context Adjustment Loss for Learned Image Compression
44. NeurIPS 2024ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
45. NeurIPS 2024CigTime: Corrective Instruction Generation Through Inverse Motion Editing
46. NeurIPS 2024CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle Detectors
47. NeurIPS 2024ColJailBreak: Collaborative Generation and Editing for Jailbreaking Text-to-Image Deep Generation
48. NeurIPS 2024Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control
49. NeurIPS 2024CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
50. NeurIPS 2024ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty

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。