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 197 篇，第 2 / 4 页

51. ICLR 2026Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention
52. ICLR 2026EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learning
53. ICLR 2026EgoWorld: Translating Exocentric View to Egocentric View using Rich Exocentric Observations
54. ICLR 2026EquAct: An SE(3)-Equivariant Multi-Task Transformer for 3D Robotic Manipulation
55. ICLR 2026ETGS: Explicit Thermodynamics Gaussian Splatting for Dynamic Thermal Reconstruction
56. ICLR 2026Exploring the Potential of Encoder-free Architectures in 3D LMMs
57. ICLR 2026Fast Estimation of Wasserstein Distances via Regression on Sliced Wasserstein Distances
58. ICLR 2026FastAvatar: Towards Unified and Fast 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformers
59. ICLR 2026FastVGGT: Fast Visual Geometry Transformer
60. ICLR 2026Feature segregation by signed weights in artificial vision systems and biological models
61. ICLR 2026Features Emerge as Discrete States: The First Application of SAEs to 3D Representations
62. ICLR 2026FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting
63. ICLR 2026Flash-Mono: Feed-Forward Accelerated Gaussian Splatting Monocular SLAM
64. ICLR 2026FlashWorld: High-quality 3D Scene Generation within Seconds
65. ICLR 2026Fracture-GS: Dynamic Fracture Simulation with Physics-Integrated Gaussian Splatting
66. ICLR 2026Frequency-aware Dynamic Gaussian Splatting
67. ICLR 2026From Cheap Geometry to Expensive Physics: Elevating Neural Operators via Latent Shape Pretraining
68. ICLR 2026From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning
69. ICLR 2026From Sparse to Dense: Spatio-Temporal Fusion for Multi-View 3D Human Pose Estimation with DenseWarper
70. ICLR 2026From Tokens to Nodes: Semantic-Guided Motion Control for Dynamic 3D Gaussian Splatting
71. ICLR 2026Fused-Planes: Why Train a Thousand Tri-Planes When You Can Share?
72. ICLR 2026G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior
73. ICLR 2026GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D Segmentation
74. ICLR 2026GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedra
75. ICLR 2026GOLDILOCS: GENERAL OBJECT-LEVEL DETECTION AND LABELING OF CHANGES IN SCENES
76. ICLR 2026GOOD: Geometry-guided Out-of-Distribution Modeling for Open-set Test-time Adaptation in Point Cloud Semantic Segmentation
77. ICLR 2026GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models
78. ICLR 2026Gradient-Direction-Aware Density Control for 3D Gaussian Splatting
79. ICLR 2026Guaranteed Simply Connected Mesh Reconstruction from an Unorganized Point Cloud
80. ICLR 2026HiDivDrop: Vision Token Reduction in MLLMs via Late Injection and Differentiable Top-K
81. ICLR 2026Horseshoe Splatting: Handling Structural Sparsity for Uncertainty-Aware Gaussian-Splatting Radiance Field Rendering
82. ICLR 2026HSIC Bottleneck for Cross-Generator and Domain-Incremental Synthetic Image Detection
83. ICLR 2026Human3R: Everyone Everywhere All at Once
84. ICLR 2026Hyden: A Hybrid Dual-Path Encoder for Monocular Geometry of High-resolution Images
85. ICLR 2026IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction
86. ICLR 2026Implicit 4D Gaussian Splatting for Fast Motion with Large Inter-Frame Displacements
87. ICLR 2026Improving 2D Diffusion Models for 3D Medical Imaging with Inter‑Slice Consistent Stochasticity
88. ICLR 2026IncVGGT: Incremental VGGT for Memory-Bounded Long-Range 3D Reconstruction
89. ICLR 2026Joint Shadow Generation and Relighting via Light-Geometry Interaction Maps
90. ICLR 2026Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields
91. ICLR 2026Learning Unified Representation of 3D Gaussian Splatting
92. ICLR 2026Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting
93. ICLR 2026LiTo: Surface Light Field Tokenization
94. ICLR 2026Locality-Attending Vision Transformer
95. ICLR 2026Low-Latency Neural LiDAR Compression with 2D Context Models
96. ICLR 2026LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context
97. ICLR 2026Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
98. ICLR 2026Mango-GS: Enhancing Spatio-Temporal Consistency in Dynamic Scenes Reconstruction using Multi-Frame Node-Guided 4D Gaussian Splatting
99. ICLR 2026MEGS^{2}: Memory-Efficient Gaussian Splatting via Spherical Gaussians and Unified Pruning
100. ICLR 2026Mesh Splatting for End-to-end Multiview Surface Reconstruction

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。