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 1,008 篇，第 16 / 21 页

  1. ICML 2026PSMix: Robust Point Cloud Recognition through Spectral Domain Mixing
  2. ICML 2026QPoint: End-to-End Lightweight Point Cloud Processing via Robust Quaternion Feature Learning
  3. ICML 2026Radial Scaling Voxelization for Accurate Small Object 3D Detection
  4. ICML 2026Rays as Pixels: Learning A Joint Distribution of Video and Camera Trajectories
  5. ICML 2026ReflFlow: Learning Geometry-Guided Ray Tracing for Dynamic Specular Reconstruction
  6. ICML 2026Rethinking Serialization in Linear 3D Vision: Decoupling Anisotropic Geometry from Isotropic Semantics
  7. ICML 2026Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction
  8. ICML 2026REViT: Roto-reflection Equivariant Convolutional Vision Transformer
  9. ICML 2026ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning
  10. ICML 2026RGGT: A Generative-Prior-Guided Transformer for Unified Rigid and Non-Rigid Point Cloud Registration
  11. ICML 2026Rh-3DGS: Robust Open-Vocabulary Scene Understanding via Riemannian Huber Distillation and Manifold-Aware Sampling
  12. ICML 2026S2GS: Streaming Semantic Gaussian Splatting for Online Scene Understanding and Reconstruction
  13. ICML 2026Scalable and Differentiable Point-Cloud Registration Using Maximum Mean Discrepancy
  14. ICML 2026Scalable Event Cloud Network for Event-based Classification
  15. ICML 2026SCRWKV: Ultra-Compact Structure-Calibrated Vision-RWKV for Topological Crack Segmentation
  16. ICML 2026SDiD：Shared diffusion prior for efficient distributed stereo image compression
  17. ICML 2026Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers
  18. ICML 2026Self-Soupervision: Cooking Model Soups without Labels
  19. ICML 2026Self-Supervised Weight Templates for Scalable Vision Model Initialization
  20. ICML 2026SG2Loc: Sequential Visual Localization on 3D Scene Graphs
  21. ICML 2026SIMPC: Learning Self-Induced Mirror-Point Consistency for Unsupervised Point Cloud Denoising
  22. ICML 2026Sinkhorn Normalization of Diffusion Kernels
  23. ICML 2026Skip-It? Theoretical Conditions for Layer Skipping in Vision–Language Models
  24. ICML 2026SMART: Scalable Mesh‑free Aerodynamic Simulations from Raw Geometries using a Transformer‑based Surrogate Model
  25. ICML 2026SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-Body Manipulation
  26. ICML 2026SpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation
  27. ICML 2026Spatio-Temporal LLM: Reasoning about Environments and Actions
  28. ICML 2026SphericalDreamer: Generating Navigable Immersive 3D Worlds with Panorama Fusion
  29. ICML 2026SpikeNet: Sparse Spike-Driven Mask Vector Transformer for Energy-Efficient and Stable Spiking Point Cloud Processing
  30. ICML 2026SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion
  31. ICML 2026Streaming Sliced Optimal Transport
  32. ICML 2026Taylor-Gaussians-Flow: Towards Non-uniform Motion for Novel View Synthesis from Monocular Video
  33. ICML 2026The Extra Tokens Matter: Disentangled Representation Learning with Vision Transformers
  34. ICML 2026TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization
  35. ICML 2026TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelity
  36. ICML 2026TopAdapter: Topology-Aware Prompt Tuning for Efficient Point Cloud Understanding
  37. ICML 2026Towards Docking-oriented De Novo Ligand Design via Gradient Inversion
  38. ICML 2026Towards Scalable and Consistent 3D Editing
  39. ICML 2026Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R
  40. ICML 2026TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and Optimization
  41. ICML 2026TVDRNet: Text-driven Viewpoint Optimization via Differentiable Rendering for 3D Reasoning Segmentation
  42. ICML 2026Utonia: Toward One Encoder for All Point Clouds
  43. ICML 2026VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks
  44. ICML 2026Vision Transformer Finetuning Benefits from Non-Smooth Components
  45. ICML 2026WhisperSplat: Lossless Steganography in 3D Gaussian Splatting
  46. ICML 2026WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
  47. ICML 2026Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation
  48. NeurIPS 2026$\alpha$Depth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion
  49. NeurIPS 2026$R^3$: 3D Reconstruction via Relative Regression
  50. NeurIPS 20263D Consistency Tokens

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