激光雷达感知论文趋势 2023–2026

主要结论

• 激光雷达感知论文从 2023 年的 84 篇增长到 2026 年的 100 篇，三年间扩大到约 1.2 倍。
• CVPR 是发激光雷达感知论文最多的会议，2023–2026 年共 242 篇，占四个会议总量的 67%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 17 篇。
• 在「自动驾驶」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的运动规划是 2.4 倍，激光雷达感知是 1.2 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 2026BiLi: Bridging the Last Mile in LiDAR Localization
• ICML 2026PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud Compression
• ICLR 2026GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception
• CVPR 2026Adaptive 3D Perception for Small Aerial Targets Under Sparse Sampling
• NeurIPS 2025Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoff
• ICML 2025Towards Learning to Complete Anything in Lidar
• ICLR 2025Point Cluster: A Compact Message Unit for Communication-Efficient Collaborative Perception
• CVPR 2025DiskVPS: Vanishing Point Detector via Hough Transform in a Disk Region
• NeurIPS 2024Inference on the Change Point under a High Dimensional Covariance Shift
• ICML 2024How Learning by Reconstruction Produces Uninformative Features For Perception
• ICLR 2024CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception
• CVPR 2024GLiDR: Topologically Regularized Graph Generative Network for Sparse LiDAR Point Clouds
• NeurIPS 2023Asynchrony-Robust Collaborative Perception via Bird's Eye View Flow
• ICML 2023Robust Perception through Equivariance
• ICLR 2023LiftedCL: Lifting Contrastive Learning for Human-Centric Perception
• CVPR 2023ALSO: Automotive Lidar Self-Supervision by Occupancy Estimation
• NeurIPS 2026CMI-Trans: Cross Modal Inconsistency-aware Transport for HSI-LiDAR Classification
• ICML 2026OBJVanish: Prompt-Driven Generation of Physically Realizable 3D LiDAR-Invisible Objects
• ICLR 2026Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud Representation
• CVPR 2026Bezier Degradation Modeling for LiDAR-based Human Motion Capture

全部激光雷达感知论文

共 86 篇，第 2 / 2 页

51. CVPR 2025V2X-R: Cooperative LiDAR-4D Radar Fusion with Denoising Diffusion for 3D Object Detection
52. CVPR 2025VISTREAM: Improving Computation Efficiency of Visual Streaming Perception via Law-of-Charge-Conservation Inspired Spiking Neural Network
53. CVPR 2025WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusion
54. ICLR 20253D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds
55. ICLR 2025GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting
56. ICLR 2025MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs
57. ICLR 2025Point Cluster: A Compact Message Unit for Communication-Efficient Collaborative Perception
58. ICLR 2025UniDrive: Towards Universal Driving Perception Across Camera Configurations
59. ICML 2025Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models
60. ICML 2025Efficient LiDAR Reflectance Compression via Scanning Serialization
61. ICML 2025How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation
62. ICML 2025Perception in Reflection
63. ICML 2025Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation
64. ICML 2025Towards Learning to Complete Anything in Lidar
65. ICML 2025Unpaired Point Cloud Completion via Unbalanced Optimal Transport
66. NeurIPS 2025D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction
67. NeurIPS 2025FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies
68. NeurIPS 2025GTR-Loc: Geospatial Text Regularization Assisted Outdoor LiDAR Localization
69. NeurIPS 2025How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?
70. NeurIPS 2025L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery
71. NeurIPS 2025Multimodal LiDAR-Camera Novel View Synthesis with Unified Pose-free Neural Fields
72. NeurIPS 2025Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoff
73. NeurIPS 2025Point Cloud Synthesis Using Inner Product Transforms
74. NeurIPS 2025Point4Bit: Post Training 4-bit Quantization for Point Cloud 3D Detection
75. NeurIPS 2025PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion
76. NeurIPS 2025PointTruss: K-Truss for Point Cloud Registration
77. NeurIPS 2025RAPID Hand: Robust, Affordable, Perception-Integrated, Dexterous Manipulation Platfrom for Embodied Intelligence
78. NeurIPS 2025RayFusion: Ray Fusion Enhanced Collaborative Visual Perception
79. NeurIPS 2025Rectified Point Flow: Generic Point Cloud Pose Estimation
80. NeurIPS 2025Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection
81. NeurIPS 2025SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving
82. NeurIPS 2025Token Embeddings Violate the Manifold Hypothesis
83. NeurIPS 2025TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception
84. NeurIPS 2025Unveiling Transformer Perception by Exploring Input Manifolds
85. NeurIPS 2025V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception
86. NeurIPS 2025What We Miss Matters: Learning from the Overlooked in Point Cloud Transformers

常见问题

2023–2026 年四大会议一共有多少篇激光雷达感知论文？

共 360 篇，按年份分别是 2023 年 84 篇、2024 年 90 篇、2025 年 86 篇、2026 年 100 篇。

NeurIPS 2026 有多少篇激光雷达感知论文？

NeurIPS 2026 有 25 篇激光雷达感知论文，上一届是 21 篇。

ICLR 2026 有多少篇激光雷达感知论文？

ICLR 2026 有 5 篇激光雷达感知论文，上一届是 5 篇。

ICML 2026 有多少篇激光雷达感知论文？

ICML 2026 有 10 篇激光雷达感知论文，上一届是 7 篇。

CVPR 2026 有多少篇激光雷达感知论文？

CVPR 2026 有 60 篇激光雷达感知论文，上一届是 53 篇。

哪个会议的激光雷达感知论文最多？

CVPR，2023–2026 年共 242 篇。