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 162 篇，第 2 / 4 页

51. ICLR 2025Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping
52. ICLR 2025Gaussian Splatting Lucas-Kanade
53. ICLR 2025Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detection
54. ICLR 2025GaussianAnything: Interactive Point Cloud Flow Matching for 3D Generation
55. ICLR 2025GaussianBlock: Building Part-Aware Compositional and Editable 3D Scene by Primitives and Gaussians
56. ICLR 2025Generalizable Human Gaussians from Single-View Image
57. ICLR 2025Generating CAD Code with Vision-Language Models for 3D Designs
58. ICLR 2025GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering
59. ICLR 2025GPS: A Probabilistic Distributional Similarity with Gumbel Priors for Set-to-Set Matching
60. ICLR 2025Graph-Guided Scene Reconstruction from Images with 3D Gaussian Splatting
61. ICLR 2025Grounding Continuous Representations in Geometry: Equivariant Neural Fields
62. ICLR 2025GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting
63. ICLR 2025GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting
64. ICLR 2025GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement
65. ICLR 2025HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents
66. ICLR 2025High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation
67. ICLR 2025HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction
68. ICLR 2025HQGS: High-Quality Novel View Synthesis with Gaussian Splatting in Degraded Scenes
69. ICLR 2025IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations
70. ICLR 2025InfoGS: Efficient Structure-Aware 3D Gaussians via Lightweight Information Shaping
71. ICLR 2025InstantSplamp: Fast and Generalizable Stenography Framework for Generative Gaussian Splatting
72. ICLR 2025Inverse Rendering using Multi-Bounce Path Tracing and Reservoir Sampling
73. ICLR 2025Latent Radiance Fields with 3D-aware 2D Representations
74. ICLR 2025Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint
75. ICLR 2025Learning 3D Perception from Others' Predictions
76. ICLR 2025Learning Equivariant Non-Local Electron Density Functionals
77. ICLR 2025Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimation
78. ICLR 2025Learning to Discretize Denoising Diffusion ODEs
79. ICLR 2025Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space
80. ICLR 2025Lightweight Predictive 3D Gaussian Splats
81. ICLR 2025Linear Spherical Sliced Optimal Transport: A Fast Metric for Comparing Spherical Data
82. ICLR 2025Linear Transformer Topological Masking with Graph Random Features
83. ICLR 2025Locality Sensitive Avatars From Video
84. ICLR 2025Locality-aware Gaussian Compression for Fast and High-quality Rendering
85. ICLR 2025LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation models
86. ICLR 2025Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
87. ICLR 2025LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias
88. ICLR 2025MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations
89. ICLR 2025Matérn Kernels for Tunable Implicit Surface Reconstruction
90. ICLR 2025Meta-Continual Learning of Neural Fields
91. ICLR 2025Metric-Driven Attributions for Vision Transformers
92. ICLR 2025MIRACLE 3D: Memory-efficient Integrated Robust Approach for Continual Learning on 3D Point Clouds via Shape Model Construction
93. ICLR 2025Model merging with SVD to tie the Knots
94. ICLR 2025MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors
95. ICLR 2025Moner: Motion Correction in Undersampled Radial MRI with Unsupervised Neural Representation
96. ICLR 2025MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
97. ICLR 2025MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection
98. ICLR 2025Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation
99. ICLR 2025Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning
100. ICLR 2025MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow

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。