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 333 篇，第 2 / 7 页

51. CVPR 2023Deep Polarization Reconstruction With PDAVIS Events
52. CVPR 2023DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization
53. CVPR 2023DegAE: A New Pretraining Paradigm for Low-Level Vision
54. CVPR 2023DepGraph: Towards Any Structural Pruning
55. CVPR 2023Depth Estimation From Camera Image and mmWave Radar Point Cloud
56. CVPR 2023DexArt: Benchmarking Generalizable Dexterous Manipulation With Articulated Objects
57. CVPR 2023DiffRF: Rendering-Guided 3D Radiance Field Diffusion
58. CVPR 2023DiffusioNeRF: Regularizing Neural Radiance Fields With Denoising Diffusion Models
59. CVPR 2023DINER: Depth-Aware Image-Based NEural Radiance Fields
60. CVPR 2023Dionysus: Recovering Scene Structures by Dividing Into Semantic Pieces
61. CVPR 2023DP-NeRF: Deblurred Neural Radiance Field With Physical Scene Priors
62. CVPR 2023DropKey for Vision Transformer
63. CVPR 2023E2PN: Efficient SE(3)-Equivariant Point Network
64. CVPR 2023EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding
65. CVPR 2023Edges to Shapes to Concepts: Adversarial Augmentation for Robust Vision
66. CVPR 2023EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points
67. CVPR 2023Efficient Hierarchical Entropy Model for Learned Point Cloud Compression
68. CVPR 2023Efficient Second-Order Plane Adjustment
69. CVPR 2023EfficientViT: Memory Efficient Vision Transformer With Cascaded Group Attention
70. CVPR 2023Enhanced Stable View Synthesis
71. CVPR 2023ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields
72. CVPR 2023EventNeRF: Neural Radiance Fields From a Single Colour Event Camera
73. CVPR 2023Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields
74. CVPR 2023Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language
75. CVPR 2023F2-NeRF: Fast Neural Radiance Field Training With Free Camera Trajectories
76. CVPR 2023FAC: 3D Representation Learning via Foreground Aware Feature Contrast
77. CVPR 2023Fast Monocular Scene Reconstruction With Global-Sparse Local-Dense Grids
78. CVPR 2023Fast Point Cloud Generation With Straight Flows
79. CVPR 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
80. CVPR 2023FlexNeRF: Photorealistic Free-Viewpoint Rendering of Moving Humans From Sparse Views
81. CVPR 2023Flow Supervision for Deformable NeRF
82. CVPR 2023FreeNeRF: Improving Few-Shot Neural Rendering With Free Frequency Regularization
83. CVPR 2023Frequency-Modulated Point Cloud Rendering With Easy Editing
84. CVPR 2023GarmentTracking: Category-Level Garment Pose Tracking
85. CVPR 2023GazeNeRF: 3D-Aware Gaze Redirection With Neural Radiance Fields
86. CVPR 2023Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process
87. CVPR 2023Generating Part-Aware Editable 3D Shapes Without 3D Supervision
88. CVPR 2023GeoMAE: Masked Geometric Target Prediction for Self-Supervised Point Cloud Pre-Training
89. CVPR 2023Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation
90. CVPR 2023GeoVLN: Learning Geometry-Enhanced Visual Representation With Slot Attention for Vision-and-Language Navigation
91. CVPR 2023Global Vision Transformer Pruning With Hessian-Aware Saliency
92. CVPR 2023GM-NeRF: Learning Generalizable Model-Based Neural Radiance Fields From Multi-View Images
93. CVPR 2023Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent With Learned Distance Functions
94. CVPR 2023GraVoS: Voxel Selection for 3D Point-Cloud Detection
95. CVPR 2023Grid-Guided Neural Radiance Fields for Large Urban Scenes
96. CVPR 2023gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction
97. CVPR 2023HandNeRF: Neural Radiance Fields for Animatable Interacting Hands
98. CVPR 2023HexPlane: A Fast Representation for Dynamic Scenes
99. CVPR 2023HGNet: Learning Hierarchical Geometry From Points, Edges, and Surfaces
100. CVPR 2023Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection

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。