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 152 篇，第 2 / 4 页

51. NeurIPS 2023Estimating Generic 3D Room Structures from 2D Annotations
52. NeurIPS 2023Exploiting Contextual Objects and Relations for 3D Visual Grounding
53. NeurIPS 2023Explore In-Context Learning for 3D Point Cloud Understanding
54. NeurIPS 2023Exploring Geometry of Blind Spots in Vision models
55. NeurIPS 2023FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models
56. NeurIPS 2023FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow
57. NeurIPS 2023FourierHandFlow: Neural 4D Hand Representation Using Fourier Query Flow
58. NeurIPS 2023Generalizable One-shot 3D Neural Head Avatar
59. NeurIPS 2023Generative Neural Fields by Mixtures of Neural Implicit Functions
60. NeurIPS 2023GenS: Generalizable Neural Surface Reconstruction from Multi-View Images
61. NeurIPS 2023Geometric Algebra Transformer
62. NeurIPS 2023Geometry-Informed Neural Operator for Large-Scale 3D PDEs
63. NeurIPS 2023GeoTMI: Predicting Quantum Chemical Property with Easy-to-Obtain Geometry via Positional Denoising
64. NeurIPS 2023Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
65. NeurIPS 2023GMSF: Global Matching Scene Flow
66. NeurIPS 2023GNeSF: Generalizable Neural Semantic Fields
67. NeurIPS 2023HeadSculpt: Crafting 3D Head Avatars with Text
68. NeurIPS 2023HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds
69. NeurIPS 2023HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception
70. NeurIPS 2023Humans in Kitchens: A Dataset for Multi-Person Human Motion Forecasting with Scene Context
71. NeurIPS 2023HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork
72. NeurIPS 2023Implicit Convolutional Kernels for Steerable CNNs
73. NeurIPS 2023InfoCD: A Contrastive Chamfer Distance Loss for Point Cloud Completion
74. NeurIPS 2023Inner-Outer Aware Reconstruction Model for Monocular 3D Scene Reconstruction
75. NeurIPS 2023Intelligent Knee Sleeves: A Real-time Multimodal Dataset for 3D Lower Body Motion Estimation Using Smart Textile
76. NeurIPS 2023Language-driven Scene Synthesis using Multi-conditional Diffusion Model
77. NeurIPS 2023LART: Neural Correspondence Learning with Latent Regularization Transformer for 3D Motion Transfer
78. NeurIPS 2023Learning Dictionary for Visual Attention
79. NeurIPS 2023Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priors
80. NeurIPS 2023LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction
81. NeurIPS 2023LightSpeed: Light and Fast Neural Light Fields on Mobile Devices
82. NeurIPS 2023Lightweight Vision Transformer with Bidirectional Interaction
83. NeurIPS 2023Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videos
84. NeurIPS 2023Lookaround Optimizer: $k$ steps around, 1 step average
85. NeurIPS 2023Lookup Table meets Local Laplacian Filter: Pyramid Reconstruction Network for Tone Mapping
86. NeurIPS 2023Lung250M-4B: A Combined 3D Dataset for CT- and Point Cloud-Based Intra-Patient Lung Registration
87. NeurIPS 2023Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction
88. NeurIPS 2023MCUFormer: Deploying Vision Tranformers on Microcontrollers with Limited Memory
89. NeurIPS 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation
90. NeurIPS 2023MiliPoint: A Point Cloud Dataset for mmWave Radar
91. NeurIPS 2023Mip-Grid: Anti-aliased Grid Representations for Neural Radiance Fields
92. NeurIPS 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset
93. NeurIPS 2023Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation
94. NeurIPS 2023NAP: Neural 3D Articulated Object Prior
95. NeurIPS 2023NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations
96. NeurIPS 2023NeRF Revisited: Fixing Quadrature Instability in Volume Rendering
97. NeurIPS 2023NeRF-IBVS: Visual Servo Based on NeRF for Visual Localization and Navigation
98. NeurIPS 2023NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries
99. NeurIPS 2023NIS3D: A Completely Annotated Benchmark for Dense 3D Nuclei Image Segmentation
100. NeurIPS 2023NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF

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。