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 211 篇，第 2 / 5 页

51. NeurIPS 2026Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localization
52. NeurIPS 2026Disentangling Channel Semantics in Vision Transformers via Token Decorrelation and Composition-Aware Modulation
53. NeurIPS 2026Do Glimpse Policies See Like Humans? A Behavioral Audit Reveals Dissociated Viewing Priors in Classification-Trained Active Vision
54. NeurIPS 2026DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers
55. NeurIPS 2026DTGS: Physics-Embedded Dynamic Thermal 3D Reconstruction with Gaussian Splatting
56. NeurIPS 2026DySurface: Consistent 4D Surface Reconstruction via Bridging Explicit Gaussians and Implicit Functions
57. NeurIPS 2026Efficient and Robust Physical 3DGS-MPM Simulation via Interior Filling and Text-Physics Optimization
58. NeurIPS 2026Efficient Transferable Optimal Transport via Min-Sliced Transport Plans
59. NeurIPS 2026EgoStream: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision
60. NeurIPS 2026EgoTac: In-the-wild Tactile Prediction from Egocentric Vision
61. NeurIPS 2026Enhancing Novel View Synthesis via Geometry Grounded Set Diffusion
62. NeurIPS 2026Evaluating Deployable Inference-Time Error Prediction in Vision MoEs
63. NeurIPS 2026Extending 3D Reconstruction Models to Any Camera
64. NeurIPS 2026Extremely Sparse-View Computed Tomography from 2D Projections via Pose-Aware Diffusion Priors
65. NeurIPS 2026Feed-Forward 3D Gaussian Splatting for High-Fidelity Animatable Hand Avatar Reconstruction from a Single Image
66. NeurIPS 2026Feedforward Novel View Synthesis for Heterogeneous Cameras
67. NeurIPS 2026Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement
68. NeurIPS 2026FlashSSM-3D: A Distilled State Space Model for Lightning-Fast Dense 3D Reconstruction
69. NeurIPS 2026FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation
70. NeurIPS 2026FocusNav: Learning Task-directed Perception via Action-Aware Future Reconstruction in Vision-and-Language Navigation
71. NeurIPS 2026FoundSurface: Feedforward Ray-Based 3D Scene Surface Reconstruction from Unposed Images
72. NeurIPS 2026FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry
73. NeurIPS 2026From Persistence to Survival: Hypothesis Testing, Effect Sizes and Vectorisation for Topological Features
74. NeurIPS 2026FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views
75. NeurIPS 2026GAMMA: Scalable 4D Gaussian Reconstruction Model for Novel View Synthesis of Monocular Videos
76. NeurIPS 2026Gaussian Density Splatting Network
77. NeurIPS 2026Gaussian Splatting-based Volumetric Video Compression with Sparse 4D Anchors
78. NeurIPS 2026Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at Once
79. NeurIPS 2026GenRec: Knowing Where to Reconstruct and Where to Generate
80. NeurIPS 2026GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
81. NeurIPS 2026Geometry-Aware Representation Denoising for Multi-view Image Restoration and 3D Reconstruction
82. NeurIPS 2026GeoPano: Towards Geometrically Accurate Panoramic 3D Reconstruction from a Single Panorama
83. NeurIPS 2026Georeferenced Cross-View 3D Reconstruction from Ground and Satellite Images
84. NeurIPS 2026GGQR: Gaussian-Grounded Query Refinement for Feed-Forward 4D Gaussian Splatting
85. NeurIPS 2026GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction
86. NeurIPS 2026Glob3R: Global Structure-from-Motion with 3D Foundation Models
87. NeurIPS 2026Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
88. NeurIPS 2026Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation
89. NeurIPS 2026HALO-VGGT: Heterogeneity-Aware Lightweight Online Compression Allocator for Efficient VGGT
90. NeurIPS 2026Hierarchical Graph Alignment for Cross-Modal 3D Scene Grounding
91. NeurIPS 2026HilbertGen-3D:Hilbert--Multifractal Conditioning for Topology-Aware 3D Generation
92. NeurIPS 2026HIST3R: Rectified State Decomposition from History for Streaming 3D Reconstruction
93. NeurIPS 2026Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion
94. NeurIPS 2026IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer
95. NeurIPS 2026Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
96. NeurIPS 2026Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
97. NeurIPS 2026LaSA-Net: A Language-Guided Network for Outdoor Generalized 3D Referring Expression Segmentation
98. NeurIPS 2026Learning Hierarchical Patch Splitting Policies for Faster Vision Transformers
99. NeurIPS 2026Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis
100. NeurIPS 2026Lookalike3D: Seeing Double in 3D

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。