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 483 篇，第 2 / 10 页

51. CVPR 2026Chain-of-Models Pre-Training Rethinking Training Acceleration of Vision Foundation Models
52. CVPR 2026Changes in Real Time Online Scene Change Detection with Multi-View
53. CVPR 2026Charge A Comprehensive Novel View Synthesis Benchmark and Dataset to
54. CVPR 2026Chorus Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding
55. CVPR 2026Clay-to-Stone Phase-wise 3D Gaussian Splatting for Monocular Articulated Hand-Object Manipulation
56. CVPR 2026ClipGStream Clip-Stream Gaussian Splatting for Any Length and Any Motion
57. CVPR 2026CLIPoint3D Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation
58. CVPR 2026CME-CAD Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation
59. CVPR 2026Color-Encoded Illumination for High-Speed Volumetric Scene Reconstruction
60. CVPR 2026Complet4R Geometric Complete 4D Reconstruction
61. CVPR 2026ComPose A Unified Completion-Pose Framework for Robust Category-Level Object Pose
62. CVPR 2026Confidence-Guided Multi-Scale Aggregation for Sparse-View High-Resolution 3D Gaussian Splatting
63. CVPR 2026CoRoGS Contextual Gaussian Splatting for Robust Large-Deviation View Synthesis
64. CVPR 2026Correspondence-Attention Alignment for Multi-View Diffusion Models
65. CVPR 2026Cross-Instance Gaussian Splatting Registration via Geometry-Aware Feature-Guided Alignment
66. CVPR 2026Cross-View Splatter Feed-Forward View Synthesis with Georeferenced Images
67. CVPR 2026CrowdGaussian Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a
68. CVPR 2026CUPID Generative 3D Reconstruction via Joint Object and Pose Modeling
69. CVPR 2026Curvature-Aware Captioning Leveraging Geodesic Attention for 3D Scene Understanding
70. CVPR 2026CycleBEV Regularizing View Transformation Networks via View Cycle Consistency for
71. CVPR 2026Dark3R Learning Structure from Motion in the Dark
72. CVPR 2026Deformation-based In-Context Learning for Point Cloud Understanding
73. CVPR 2026Dehallu3D Hallucination-Mitigated 3D Generation from a Single Image via Cyclic
74. CVPR 2026Depth Any Endoscopy Towards Self-Supervised Generalizable Depth Estimation in Monocular
75. CVPR 2026Depth Peeling for High-Fidelity Gaussian-Enhanced Surfel Rendering
76. CVPR 2026Dexterous World Models
77. CVPR 2026DiffBMP Differentiable Rendering with Bitmap Primitives
78. CVPR 2026Differentiable Stroke Planning with Dual Parameterization for Efficient and High-Fidelity
79. CVPR 2026DiffSoup Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance
80. CVPR 2026DiffusionHarmonizer Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion
81. CVPR 2026DirectFisheye-GS Enabling Native Fisheye Input in Gaussian Splatting with Cross-View
82. CVPR 2026Direction-aware 3D Large Multimodal Models
83. CVPR 2026Disco-GS Gaussian Splatting in Dynamic Color Lighting
84. CVPR 2026Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting
85. CVPR 2026DualPrim Compact 3D Reconstruction with Positive and Negative Primitives
86. CVPR 2026DualSplat Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction
87. CVPR 2026Dynamic Black-hole Emission Tomography with Physics-informed Neural Fields
88. CVPR 2026Dynamic Visual SLAM using a General 3D Prior
89. CVPR 2026Dynamic-eDiTor Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer
90. CVPR 2026Dynamic-Static Decomposition for Novel View Synthesis of Dynamic Scenes with
91. CVPR 2026DynamicTree Interactive Real Tree Animation via Sparse Voxel Spectrum
92. CVPR 2026DynamicVGGT Learning Dynamic Point Maps for 4D Scene Reconstruction in
93. CVPR 2026E-RayZer Self-supervised 3D Reconstruction as Spatial Visual Pre-training
94. CVPR 2026E2EGS Event-to-Edge Gaussian Splatting for Pose-Free 3D Reconstruction
95. CVPR 2026EcoSplat Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images
96. CVPR 2026Edge-RecViT Efficient Vision Transformer via Semantic-Refined Dynamic Recursion
97. CVPR 2026EDGS Eliminating Densification for Efficient Convergence of 3DGS
98. CVPR 2026Edit-aware RAW reconstruction
99. CVPR 2026EEGiT Teaching Vision Transformers to Understand the EEG signal
100. CVPR 2026Efficient Encoder-Free Fourier-based 3D Large Multimodal Model

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。