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 3 / 4 页

101. ICLR 2025ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction
102. ICLR 2025NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields
103. ICLR 2025Neural Eulerian Scene Flow Fields
104. ICLR 2025NeuralPlane: Structured 3D Reconstruction in Planar Primitives with Neural Fields
105. ICLR 2025NextBestPath: Efficient 3D Mapping of Unseen Environments
106. ICLR 2025No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
107. ICLR 2025Not-So-Optimal Transport Flows for 3D Point Cloud Generation
108. ICLR 2025Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy
109. ICLR 2025OMG: Opacity Matters in Material Modeling with Gaussian Splatting
110. ICLR 2025OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation
111. ICLR 2025OmniRe: Omni Urban Scene Reconstruction
112. ICLR 2025On Scaling Up 3D Gaussian Splatting Training
113. ICLR 2025On the Fourier analysis in the SO(3) space : the EquiLoPO Network
114. ICLR 2025Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation
115. ICLR 2025PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer
116. ICLR 2025Pedestrian Motion Reconstruction: A Large-scale Benchmark via Mixed Reality Rendering with Multiple Perspectives and Modalities
117. ICLR 2025PIN: Prolate Spheroidal Wave Function-based Implicit Neural Representations
118. ICLR 2025PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance
119. ICLR 2025Point-based Instance Completion with Scene Constraints
120. ICLR 2025Point-SAM: Promptable 3D Segmentation Model for Point Clouds
121. ICLR 2025Poison-splat: Computation Cost Attack on 3D Gaussian Splatting
122. ICLR 2025PolaFormer: Polarity-aware Linear Attention for Vision Transformers
123. ICLR 2025PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify
124. ICLR 2025PvNeXt: Rethinking Network Design and Temporal Motion for Point Cloud Video Recognition
125. ICLR 2025RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation
126. ICLR 2025Reflective Gaussian Splatting
127. ICLR 2025RelitLRM: Generative Relightable Radiance for Large Reconstruction Models
128. ICLR 2025ReMatching Dynamic Reconstruction Flow
129. ICLR 2025RESfM: Robust Deep Equivariant Structure from Motion
130. ICLR 2025Rethinking Spiking Neural Networks from an Ensemble Learning Perspective
131. ICLR 2025Retri3D: 3D Neural Graphics Representation Retrieval
132. ICLR 2025Revealing the 3D Cosmic Web through Gravitationally Constrained Neural Fields
133. ICLR 2025RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object Detection
134. ICLR 2025SC-OmniGS: Self-Calibrating Omnidirectional Gaussian Splatting
135. ICLR 2025Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video
136. ICLR 2025SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography
137. ICLR 2025Shape as Line Segments: Accurate and Flexible Implicit Surface Representation
138. ICLR 2025SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training
139. ICLR 2025Sort-free Gaussian Splatting via Weighted Sum Rendering
140. ICLR 2025SPA: 3D Spatial-Awareness Enables Effective Embodied Representation
141. ICLR 2025Spiking Vision Transformer with Saccadic Attention
142. ICLR 2025SplatFormer: Point Transformer for Robust 3D Gaussian Splatting
143. ICLR 2025SplineGS: Learning Smooth Trajectories in Gaussian Splatting for Dynamic Scene Reconstruction
144. ICLR 2025State Space Model Meets Transformer: A New Paradigm for 3D Object Detection
145. ICLR 2025SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency
146. ICLR 2025Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene
147. ICLR 2025TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes
148. ICLR 2025The 3D-PC: a benchmark for visual perspective taking in humans and machines
149. ICLR 2025ThermalGaussian: Thermal 3D Gaussian Splatting
150. ICLR 2025Think Then React: Towards Unconstrained Action-to-Reaction Motion Generation

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。