三维视觉论文趋势 2023–2026
三维重建与神经渲染
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 3,226 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 152 | 56 | 22 | 333 | 563 |
| 2024 | 222 | 96 | 44 | 389 | 751 |
| 2025 | 254 | 162 | 52 | 434 | 902 |
| 2026 | 211 | 197 | 117 | 485 | 1,010 |
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 511 篇，第 9 / 11 页
- ICLR 2024Initializing Models with Larger Ones
- ICLR 2024InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
- ICLR 2024Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model
- ICLR 2024InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image
- ICLR 2024Latent 3D Graph Diffusion
- ICLR 2024LEAP: Liberate Sparse-View 3D Modeling from Camera Poses
- ICLR 2024Learning 3D Particle-based Simulators from RGB-D Videos
- ICLR 2024Learning Implicit Representation for Reconstructing Articulated Objects
- ICLR 2024Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation
- ICLR 2024Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation
- ICLR 2024LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection
- ICLR 2024LRM: Large Reconstruction Model for Single Image to 3D
- ICLR 2024MagicDrive: Street View Generation with Diverse 3D Geometry Control
- ICLR 2024Mask-Based Modeling for Neural Radiance Fields
- ICLR 2024MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection
- ICLR 2024MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Field
- ICLR 2024Multi-View Representation is What You Need for Point-Cloud Pre-Training
- ICLR 2024Neural Field Classifiers via Target Encoding and Classification Loss
- ICLR 2024Neural Polynomial Gabor Fields for Macro Motion Analysis
- ICLR 2024Neural Processing of Tri-Plane Hybrid Neural Fields
- ICLR 2024Neural SDF Flow for 3D Reconstruction of Dynamic Scenes
- ICLR 2024OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views
- ICLR 2024PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction
- ICLR 2024Point2SSM: Learning Morphological Variations of Anatomies from Point Clouds
- ICLR 2024Pooling Image Datasets with Multiple Covariate Shift and Imbalance
- ICLR 2024PORF: POSE RESIDUAL FIELD FOR ACCURATE NEURAL SURFACE RECONSTRUCTION
- ICLR 2024Pose Modulated Avatars from Video
- ICLR 2024Pre-training LiDAR-based 3D Object Detectors through Colorization
- ICLR 2024Pseudo-Generalized Dynamic View Synthesis from a Video
- ICLR 2024Quasi-Monte Carlo for 3D Sliced Wasserstein
- ICLR 2024Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting
- ICLR 2024Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
- ICLR 2024REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning
- ICLR 2024ResFields: Residual Neural Fields for Spatiotemporal Signals
- ICLR 2024Semantic Flow: Learning Semantic Fields of Dynamic Scenes from Monocular Videos
- ICLR 2024SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation
- ICLR 2024Skip-Attention: Improving Vision Transformers by Paying Less Attention
- ICLR 2024Sliced Wasserstein Estimation with Control Variates
- ICLR 2024SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation
- ICLR 2024SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition
- ICLR 2024Symbol as Points: Panoptic Symbol Spotting via Point-based Representation
- ICLR 2024SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
- ICLR 2024Synergistic Patch Pruning for Vision Transformer: Unifying Intra- & Inter-Layer Patch Importance
- ICLR 2024Towards 3D Molecule-Text Interpretation in Language Models
- ICLR 2024Towards Category Unification of 3D Single Object Tracking on Point Clouds
- ICLR 2024Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators
- ICLR 2024TUVF: Learning Generalizable Texture UV Radiance Fields
- ICLR 2024UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous Driving
- ICLR 2024Uni3D: Exploring Unified 3D Representation at Scale
- ICLR 2024Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查三维视觉在 CVPR 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "3d-vision"}
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。