三维视觉论文趋势 2023–2026

主要结论

• 三维视觉论文从 2023 年的 563 篇增长到 2026 年的 1,010 篇，三年间扩大到约 1.8 倍。
• CVPR 是发三维视觉论文最多的会议，2023–2026 年共 1,641 篇，占四个会议总量的 51%。
• 交叉方向里涨得最快的是高斯过程：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 158 篇。
• 在「计算机视觉」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的视频理解是 2.6 倍，三维视觉是 1.8 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$\alpha$Depth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion
• ICML 20263D MeanFlow: One-Step Point Cloud Completion and Generation via Average-Velocity Transport
• ICLR 2026$\pi^3$: Permutation-Equivariant Visual Geometry Learning
• CVPR 20262D-LFM Lifting Foundation Model without 3D Supervision
• NeurIPS 20251000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering
• ICML 20253D-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric Priors
• ICLR 20253D StreetUnveiler with Semantic-aware 2DGS - a simple baseline
• CVPR 20253D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes
• NeurIPS 20243D Gaussian Rendering Can Be Sparser: Efficient Rendering via Learned Fragment Pruning
• ICML 20243D Geometric Shape Assembly via Efficient Point Cloud Matching
• ICLR 20243D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining
• CVPR 2024DaReNeRF: Direction-aware Representation for Dynamic Scenes
• NeurIPS 2023[Re] Masked Autoencoders Are Small Scale Vision Learners: A Reproduction Under Resource Constraints
• ICML 2023Efficient Graph Field Integrators Meet Point Clouds
• ICLR 2023$\mathrm{SE}(3)$-Equivariant Attention Networks for Shape Reconstruction in Function Space
• CVPR 20233D Cinemagraphy From a Single Image
• NeurIPS 2026$R^3$: 3D Reconstruction via Relative Regression
• ICML 20263DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification
• ICLR 20263DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic Cameras
• CVPR 20263D Gaussian Splatting at Arbitrary Resolutions with Compact Proxy Anchors

全部三维视觉论文

共 96 篇，第 2 / 2 页

51. ICLR 2024Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation
52. ICLR 2024LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection
53. ICLR 2024LRM: Large Reconstruction Model for Single Image to 3D
54. ICLR 2024MagicDrive: Street View Generation with Diverse 3D Geometry Control
55. ICLR 2024Mask-Based Modeling for Neural Radiance Fields
56. ICLR 2024MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection
57. ICLR 2024MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Field
58. ICLR 2024Multi-View Representation is What You Need for Point-Cloud Pre-Training
59. ICLR 2024Neural Field Classifiers via Target Encoding and Classification Loss
60. ICLR 2024Neural Polynomial Gabor Fields for Macro Motion Analysis
61. ICLR 2024Neural Processing of Tri-Plane Hybrid Neural Fields
62. ICLR 2024Neural SDF Flow for 3D Reconstruction of Dynamic Scenes
63. ICLR 2024OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views
64. ICLR 2024PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction
65. ICLR 2024Point2SSM: Learning Morphological Variations of Anatomies from Point Clouds
66. ICLR 2024Pooling Image Datasets with Multiple Covariate Shift and Imbalance
67. ICLR 2024PORF: POSE RESIDUAL FIELD FOR ACCURATE NEURAL SURFACE RECONSTRUCTION
68. ICLR 2024Pose Modulated Avatars from Video
69. ICLR 2024Pre-training LiDAR-based 3D Object Detectors through Colorization
70. ICLR 2024Pseudo-Generalized Dynamic View Synthesis from a Video
71. ICLR 2024Quasi-Monte Carlo for 3D Sliced Wasserstein
72. ICLR 2024Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting
73. ICLR 2024Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
74. ICLR 2024REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning
75. ICLR 2024ResFields: Residual Neural Fields for Spatiotemporal Signals
76. ICLR 2024Semantic Flow: Learning Semantic Fields of Dynamic Scenes from Monocular Videos
77. ICLR 2024SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation
78. ICLR 2024Skip-Attention: Improving Vision Transformers by Paying Less Attention
79. ICLR 2024Sliced Wasserstein Estimation with Control Variates
80. ICLR 2024SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation
81. ICLR 2024SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition
82. ICLR 2024Symbol as Points: Panoptic Symbol Spotting via Point-based Representation
83. ICLR 2024SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
84. ICLR 2024Synergistic Patch Pruning for Vision Transformer: Unifying Intra- & Inter-Layer Patch Importance
85. ICLR 2024Towards 3D Molecule-Text Interpretation in Language Models
86. ICLR 2024Towards Category Unification of 3D Single Object Tracking on Point Clouds
87. ICLR 2024Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators
88. ICLR 2024TUVF: Learning Generalizable Texture UV Radiance Fields
89. ICLR 2024UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous Driving
90. ICLR 2024Uni3D: Exploring Unified 3D Representation at Scale
91. ICLR 2024Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels
92. ICLR 2024USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields
93. ICLR 2024V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection
94. ICLR 2024Vision Transformers Need Registers
95. ICLR 2024WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space
96. ICLR 2024Win-Win: Training High-Resolution Vision Transformers from Two Windows

常见问题

2023–2026 年四大会议一共有多少篇三维视觉论文？

共 3,226 篇，按年份分别是 2023 年 563 篇、2024 年 751 篇、2025 年 902 篇、2026 年 1,010 篇。

NeurIPS 2026 有多少篇三维视觉论文？

NeurIPS 2026 有 211 篇三维视觉论文，上一届是 254 篇。

ICLR 2026 有多少篇三维视觉论文？

ICLR 2026 有 197 篇三维视觉论文，上一届是 162 篇。

ICML 2026 有多少篇三维视觉论文？

ICML 2026 有 117 篇三维视觉论文，上一届是 52 篇。

CVPR 2026 有多少篇三维视觉论文？

CVPR 2026 有 485 篇三维视觉论文，上一届是 434 篇。

哪个会议的三维视觉论文最多？

CVPR，2023–2026 年共 1,641 篇。