运动规划论文趋势 2023–2026

主要结论

• 运动规划论文从 2023 年的 34 篇增长到 2026 年的 83 篇，三年间扩大到约 2.4 倍。
• CVPR 是发运动规划论文最多的会议，2023–2026 年共 115 篇，占四个会议总量的 51%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 2 篇增至 2026 年的 16 篇。
• 在「自动驾驶」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的占用预测是 2.3 倍，运动规划是 2.4 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 2026Coherence-Aware Transition-Intent Fusion for LTL Planning under Uncertain Semantic Maps
• ICML 2026Trajectory-Aware Heuristic Learning for Combinatorial Search
• ICLR 2026Efficient Differentiable Contact Model with Long-range Influence
• CVPR 2026EgoPoseFormer v2 Accurate Egocentric Human Motion Estimation for ARVR
• NeurIPS 2025Place Cells as Multi-Scale Position Embeddings: Random Walk Transition Kernels for Path Planning
• ICML 2025Goal-Space Planning with Subgoal Models
• ICLR 20253DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
• CVPR 2025A Polarization-Aided Transformer for Image Deblurring via Motion Vector Decomposition
• NeurIPS 2024Text to Blind Motion
• ICML 2024Bringing Motion Taxonomies to Continuous Domains via GPLVM on Hyperbolic manifolds
• ICLR 2024Grounding Language Plans in Demonstrations Through Counterfactual Perturbations
• CVPR 2024DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning
• NeurIPS 2023Accelerating Motion Planning via Optimal Transport
• ICML 2023Motion Question Answering via Modular Motion Programs
• ICLR 2023Integrating Symmetry into Differentiable Planning with Steerable Convolutions
• CVPR 20233D-POP - An Automated Annotation Approach to Facilitate Markerless 2D-3D Tracking of Freely Moving Birds With Marker-Based Motion Capture
• NeurIPS 2026ControlJEPA: Principled Trajectory Regularization via Lyapunov Tube Loss
• ICML 2026Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing
• ICLR 2026NeMo-map: Neural Implicit Flow Fields for Spatio-Temporal Motion Mapping
• CVPR 2026Event-based Motion Deblurring with Unpaired Data

全部运动规划论文

共 53 篇，第 1 / 2 页

1. CVPR 2024AAMDM: Accelerated Auto-regressive Motion Diffusion Model
2. CVPR 2024Arbitrary Motion Style Transfer with Multi-condition Motion Latent Diffusion Model
3. CVPR 2024AvatarGPT: All-in-One Framework for Motion Understanding Planning Generation and Beyond
4. CVPR 2024DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning
5. CVPR 2024Detector-Free Structure from Motion
6. CVPR 2024Effective Video Mirror Detection with Inconsistent Motion Cues
7. CVPR 2024HardMo: A Large-Scale Hardcase Dataset for Motion Capture
8. CVPR 2024Implicit Motion Function
9. CVPR 2024IQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation
10. CVPR 2024Learned Trajectory Embedding for Subspace Clustering
11. CVPR 2024Learning Structure-from-Motion with Graph Attention Networks
12. CVPR 2024Loose Inertial Poser: Motion Capture with IMU-attached Loose-Wear Jacket
13. CVPR 2024MoST: Motion Style Transformer Between Diverse Action Contents
14. CVPR 2024Motion Blur Decomposition with Cross-shutter Guidance
15. CVPR 2024Motion Diversification Networks
16. CVPR 2024Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring
17. CVPR 2024On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving
18. CVPR 2024Optimizing Diffusion Noise Can Serve As Universal Motion Priors
19. CVPR 2024PAPR in Motion: Seamless Point-level 3D Scene Interpolation
20. CVPR 2024ProMotion: Prototypes As Motion Learners
21. CVPR 2024READ: Retrieval-Enhanced Asymmetric Diffusion for Motion Planning
22. CVPR 2024RoHM: Robust Human Motion Reconstruction via Diffusion
23. CVPR 2024Seamless Human Motion Composition with Blended Positional Encodings
24. CVPR 2024Seeing Motion at Nighttime with an Event Camera
25. CVPR 2024SingularTrajectory: Universal Trajectory Predictor Using Diffusion Model
26. CVPR 2024SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction
27. CVPR 2024Sparse Global Matching for Video Frame Interpolation with Large Motion
28. CVPR 2024Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment
29. CVPR 2024Tri-Modal Motion Retrieval by Learning a Joint Embedding Space
30. CVPR 2024VGGSfM: Visual Geometry Grounded Deep Structure From Motion
31. CVPR 2024WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion
32. CVPR 2024Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos
33. ICLR 2024CrossLoco: Human Motion Driven Control of Legged Robots via Guided Unsupervised Reinforcement Learning
34. ICLR 2024Grounding Language Plans in Demonstrations Through Counterfactual Perturbations
35. ICLR 2024RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches
36. ICLR 2024SEPT: Towards Efficient Scene Representation Learning for Motion Prediction
37. ICLR 2024Single Motion Diffusion
38. ICML 2024Bringing Motion Taxonomies to Continuous Domains via GPLVM on Hyperbolic manifolds
39. ICML 2024DNCs Require More Planning Steps
40. ICML 2024Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring
41. ICML 2024Position: LLMs Can’t Plan, But Can Help Planning in LLM-Modulo Frameworks
42. ICML 2024Potential Based Diffusion Motion Planning
43. ICML 2024Prototypical Transformer As Unified Motion Learners
44. ICML 2024RoboMP$^2$: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models
45. NeurIPS 2024ALPINE: Unveiling The Planning Capability of Autoregressive Learning in Language Models
46. NeurIPS 2024In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before an Ongoing Trajectory Terminates
47. NeurIPS 2024Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference
48. NeurIPS 2024Learning Cooperative Trajectory Representations for Motion Forecasting
49. NeurIPS 2024Model-based Diffusion for Trajectory Optimization
50. NeurIPS 2024Revisiting motion information for RGB-Event tracking with MOT philosophy

常见问题

2023–2026 年四大会议一共有多少篇运动规划论文？

共 225 篇，按年份分别是 2023 年 34 篇、2024 年 53 篇、2025 年 55 篇、2026 年 83 篇。

NeurIPS 2026 有多少篇运动规划论文？

NeurIPS 2026 有 28 篇运动规划论文，上一届是 12 篇。

ICLR 2026 有多少篇运动规划论文？

ICLR 2026 有 8 篇运动规划论文，上一届是 11 篇。

ICML 2026 有多少篇运动规划论文？

ICML 2026 有 10 篇运动规划论文，上一届是 5 篇。

CVPR 2026 有多少篇运动规划论文？

CVPR 2026 有 37 篇运动规划论文，上一届是 27 篇。

哪个会议的运动规划论文最多？

CVPR，2023–2026 年共 115 篇。