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

每年论文数

各会议论文数

按年份和会议统计

三维视觉论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20231525622333563
20242229644389751
202525416252434902
20262111971174851,010

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

全部三维视觉论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 3,224 篇，第 14 / 65 页

  1. ICLR 2026TIGaussian: Disentangle Gaussians for Spatial-Awared Text-Image-3D Alignment
  2. ICLR 2026TINKER: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization
  3. ICLR 2026To Augment or Not to Augment? Diagnosing Distributional Symmetry Breaking
  4. ICLR 2026To View Transform or Not to View Transform: NeRF-based Pre-training Perspective
  5. ICLR 2026Towards Physically Executable 3D Gaussian for Embodied Navigation
  6. ICLR 2026True Self-Supervised Novel View Synthesis is Transferable
  7. ICLR 2026TTT3R: 3D Reconstruction as Test-Time Training
  8. ICLR 2026UFO-4D: Unposed Feedforward 4D reconstruction from Two Images
  9. ICLR 2026ULTRA-360: Unconstrained Dataset for Large-scale Temporal 3D Reconstruction across Altitudes and Omnidirectional Views
  10. ICLR 2026UltraGauss: Ultrafast Gaussian Reconstruction of 3D Ultrasound Volumes
  11. ICLR 2026Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction
  12. ICLR 2026Uncertainty-Aware 3D Reconstruction for Dynamic Underwater Scenes
  13. ICLR 2026Uncertainty-Aware Gaussian Map for Vision-Language Navigation
  14. ICLR 2026Unified 3D Scene Understanding Through Physical World Modeling
  15. ICLR 2026UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstruction
  16. ICLR 2026UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding
  17. ICLR 2026Universal Beta Splatting
  18. ICLR 2026UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections
  19. ICLR 2026UrbanGS: Efficient and Scalable Architecture for Geometrically Accurate Large-Scene Reconstruction
  20. ICLR 2026Variation-aware Flexible 3D Gaussian Editing
  21. ICLR 2026VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Pottery
  22. ICLR 2026VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing
  23. ICLR 2026Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction–Reasoning Synergy
  24. ICLR 2026VisionLaw: Inferring Interpretable Intrinsic Dynamics from Visual Observations via Bilevel Optimization
  25. ICLR 2026VoMP: Predicting Volumetric Mechanical Property Fields
  26. ICLR 2026Vulcan: Crafting Compact Class-Specific Vision Transformers For Edge Intelligence
  27. ICLR 2026Weight Space Representation Learning on Diverse NeRF Architectures
  28. ICLR 2026WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool
  29. ICLR 2026WorldTree: Towards 4D Dynamic Worlds from Monocular Video using Tree-Chains
  30. ICLR 2026YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting
  31. ICML 20263D MeanFlow: One-Step Point Cloud Completion and Generation via Average-Velocity Transport
  32. ICML 20263D Scene Assertion Verification
  33. ICML 20263DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification
  34. ICML 20263DGS$^2$-TR: A Scalable Second-Order Trust-Region Method for 3D Gaussian Splatting
  35. ICML 20264DPC$^2$hat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping
  36. ICML 20264RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere
  37. ICML 2026A Robust Optimization Guided Pruning Framework for Vision and Large Language Models
  38. ICML 2026AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editing
  39. ICML 2026Affine-Equivariant Kernel Space Encoding for NeRF Editing
  40. ICML 2026Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds
  41. ICML 2026ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
  42. ICML 2026AvAtar: Learning to Align via Active Optimal Transport
  43. ICML 2026Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting
  44. ICML 2026Compass-RoPE: Isotropic Rotary Position Embeddings for Vision Transformers
  45. ICML 2026Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models
  46. ICML 2026Continuous Viewpoint Adaptation for Single View 3D Object Reconstruction
  47. ICML 2026Counterfactual Occlusion-Aware Learning via Visibility Intervention for LiDAR Anomaly Detection
  48. ICML 2026CoverPruneGS: Coverage-Preserving Structured Pruning for Hierarchical 3D Gaussian Splatting from Sparse-View Monocular Videos
  49. ICML 2026Creat3r: Confidence Reaggregation for Exploration-aware Active 3D Reconstruction
  50. ICML 2026De4D-SLAM: Gradient-Isolated Static-Dynamic Decoupling for Monocular SLAM in Dynamic Environments

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"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「计算机视觉」下的其他主题