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 20 / 21 页

  1. NeurIPS 2026RigRecon: Efficient Rig-Aware Street Reconstruction via Dual-Path Spatio-Temporal Interaction
  2. NeurIPS 2026Robust and Efficient Finetuning of Vision Foundation Models via Implicit Ensembling
  3. NeurIPS 2026Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation
  4. NeurIPS 2026RoSeViT: Role-Separated Vision Transformers for ARC Visual Reasoning
  5. NeurIPS 2026RSPReg: Reliability-aware Structural Prototype Learning for Point Cloud Registration
  6. NeurIPS 2026SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild
  7. NeurIPS 2026Scaffold3D: SfM-Conditioned Pointmap Prediction for Multi-View 3D Reconstruction
  8. NeurIPS 2026Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video
  9. NeurIPS 2026Scaling Optimization-Oriented Hypernetworks for Implicit Neural Representations
  10. NeurIPS 2026SCION: Scene Composition via Instanced Neural Primitives
  11. NeurIPS 2026scShapeBench: Discovering geometry from high dimensional scRNAseq data
  12. NeurIPS 2026Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images
  13. NeurIPS 2026Seg3DParts: Segmentation-Grounded Controllable Part-Level 3D Generation
  14. NeurIPS 2026SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning
  15. NeurIPS 2026SOLA: A Structured Operator Library for Attention in Pretrained Vision Transformers
  16. NeurIPS 2026Sophon: A Procedural Diagnostic for Spatial Reasoning in Vision-Language Models
  17. NeurIPS 2026Spectrally Parameterized Neural Inverse Reconstruction
  18. NeurIPS 2026Spherical Bayesian Experimental Design for Active View Selection in 3D Gaussian Splatting
  19. NeurIPS 2026Spik-NeRF v2: Pushing the Limit of Spiking Neural Radiance Fields with $ \pm $I-LIF
  20. NeurIPS 2026Splatting the Invisible: Geometry and Appearance Scene Completion from Sparse Views
  21. NeurIPS 2026Split-and-scale Latent 3D Representations
  22. NeurIPS 2026SpRePE: A Spherical Geometry-Aware Position Embedding scheme for Vision Transformers
  23. NeurIPS 2026Stable3R: Streaming 3D Reconstruction with Stable Geometric References
  24. NeurIPS 2026State Evolution Awareness for Category-agnostic 3D Point Cloud Tracking
  25. NeurIPS 2026StereoSplat: Metric-Scale Novel View Synthesis via Stereo-Grounded Gaussian Splatting
  26. NeurIPS 2026SurGe: Improved Surface Geometry in Point Maps
  27. NeurIPS 2026SVG-3D: Mining Decision Boundaries with Generative Splatting Priors for Zero-Shot 3D Classification
  28. NeurIPS 2026SynGS: Synergistic Continual Learning and Change Detection with Gaussian Splatting
  29. NeurIPS 2026T$^2$-Splat: Adaptive Topology Mesh Splatting with Texture Residuals
  30. NeurIPS 2026Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces
  31. NeurIPS 2026TESLA: Native 4D Gaussian Splatting Generation with Temporally Structured Latents
  32. NeurIPS 2026Text as Partial Constraint: Core–Residual Alignment for Robust Vision–Language Learning
  33. NeurIPS 2026The Mask Is Not the Object: Volumetric Supervision for 3D Gaussian Segmentation
  34. NeurIPS 2026Think Before You Generate: Active Panoramic Exploration for Text-to-3D Scenes
  35. NeurIPS 2026Towards Matrix-Parallel and Feature-Scalable 3D Gaussian Splatting Rendering on GPUs
  36. NeurIPS 2026Towards Reconstructing Geographically Diverse Architecture with 3D Foundation Models
  37. NeurIPS 2026TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
  38. NeurIPS 2026Training Vision Transformers to Focus: Emergence of Attention Head Specialization
  39. NeurIPS 2026TransmissiveGS: Residual-Guided Disentangled Gaussian Splatting for Transmissive Scene Reconstruction and Rendering
  40. NeurIPS 2026Trellis4D: Complex 4D Mesh Generation
  41. NeurIPS 2026U-MVP: Encode Locally, Decode Globally for Feed-Forward 3D Gaussian Splatting
  42. NeurIPS 2026UltraVoxelGS: Voxel-First Feed-Forward Gaussian Splatting for 3D Ultrasound Reconstruction
  43. NeurIPS 2026Understanding Multi-View Transformers
  44. NeurIPS 2026Unified Loss-Aware Density Control for 3D Gaussian Splatting
  45. NeurIPS 2026Unified Panoramic Geometry Estimation via Multi-View Foundation Models
  46. NeurIPS 2026UniGS: Unified Geometry-Aware Gaussian Splatting for Multimodal Rendering
  47. NeurIPS 2026UniReFP: Robust Unified Fingerprinting for Vision Models against Cross-Task Repurposing Attacks
  48. NeurIPS 2026Vision Correlators: Correlation-Driven Visual Understanding with Hypergraphs
  49. NeurIPS 2026Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration
  50. NeurIPS 2026Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images

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