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 170 篇，第 1 / 4 页

1. NeurIPS 2023[Re] End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking
2. NeurIPS 20234D Panoptic Scene Graph Generation
3. NeurIPS 2023A case for reframing automated medical image classification as segmentation
4. NeurIPS 2023A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)
5. NeurIPS 2023A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems
6. NeurIPS 2023A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset
7. NeurIPS 2023A Unified Conditional Framework for Diffusion-based Image Restoration
8. NeurIPS 2023AbDiffuser: full-atom generation of in-vitro functioning antibodies
9. NeurIPS 2023Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs
10. NeurIPS 2023Alleviating the Semantic Gap for Generalized fMRI-to-Image Reconstruction
11. NeurIPS 2023Amazon-M2: A Multilingual Multi-locale Shopping Session Dataset for Recommendation and Text Generation
12. NeurIPS 2023Analyzing the Sample Complexity of Self-Supervised Image Reconstruction Methods
13. NeurIPS 2023AND: Adversarial Neural Degradation for Learning Blind Image Super-Resolution
14. NeurIPS 2023AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation
15. NeurIPS 2023Are These the Same Apple? Comparing Images Based on Object Intrinsics
16. NeurIPS 2023ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections
17. NeurIPS 2023Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment
18. NeurIPS 2023Benchmarking and Analyzing 3D-aware Image Synthesis with a Modularized Codebase
19. NeurIPS 2023Benchmarking Robustness to Adversarial Image Obfuscations
20. NeurIPS 2023Beyond MLE: Convex Learning for Text Generation
21. NeurIPS 2023Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense
22. NeurIPS 2023Black-box Backdoor Defense via Zero-shot Image Purification
23. NeurIPS 2023BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing
24. NeurIPS 2023Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?
25. NeurIPS 2023CELLE-2: Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transformer
26. NeurIPS 2023ChatGPT-Powered Hierarchical Comparisons for Image Classification
27. NeurIPS 2023Cocktail: Mixing Multi-Modality Control for Text-Conditional Image Generation
28. NeurIPS 2023COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs
29. NeurIPS 2023Cola: A Benchmark for Compositional Text-to-image Retrieval
30. NeurIPS 2023Conditional Score Guidance for Text-Driven Image-to-Image Translation
31. NeurIPS 2023ConRad: Image Constrained Radiance Fields for 3D Generation from a Single Image
32. NeurIPS 2023Constructing Non-isotropic Gaussian Diffusion Model Using Isotropic Gaussian Diffusion Model for Image Editing
33. NeurIPS 2023Controlling Text-to-Image Diffusion by Orthogonal Finetuning
34. NeurIPS 2023Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems
35. NeurIPS 2023CorresNeRF: Image Correspondence Priors for Neural Radiance Fields
36. NeurIPS 2023Counterfactual Generation with Identifiability Guarantees
37. NeurIPS 2023Customizable Image Synthesis with Multiple Subjects
38. NeurIPS 2023CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation
39. NeurIPS 2023Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation
40. NeurIPS 2023Decorate3D: Text-Driven High-Quality Texture Generation for Mesh Decoration in the Wild
41. NeurIPS 2023DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis
42. NeurIPS 2023DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology
43. NeurIPS 2023DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models
44. NeurIPS 2023DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model
45. NeurIPS 2023Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels
46. NeurIPS 2023Diffusion Self-Guidance for Controllable Image Generation
47. NeurIPS 2023Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
48. NeurIPS 2023Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback
49. NeurIPS 2023Dream the Impossible: Outlier Imagination with Diffusion Models
50. NeurIPS 2023DreamHuman: Animatable 3D Avatars from Text

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。