mlsanityData to 7 Oct 2026

Single-Eye View: Monocular Real-time Perception Package for Autonomous Driving

arXiv 2603.21061 ↗First posted 22 Mar 2026cs.CVcited by 0

On the map: End-to-end autonomous driving → VLMs for autonomous driving

Abstract (arXiv)

Amidst the rapid advancement of camera-based autonomous driving technology, effectiveness is often prioritized with limited attention to computational efficiency. To address this issue, this paper introduces LRHPerception, a real-time monocular perception package for autonomous driving that uses single-view camera video to interpret the surrounding environment. The proposed system combines the computational efficiency of end-to-end learning with the rich representational detail of local mapping methodologies. With significant improvements in object tracking and prediction, road segmentation, and depth estimation integrated into a unified framework, LRHPerception processes monocular image data into a five-channel tensor consisting of RGB, road segmentation, and pixel-level depth estimation, augmented with object detection and trajectory prediction. Experimental results demonstrate strong performance, achieving real-time processing at 29 FPS on a single GPU, representing a 555% speedup over the fastest mapping-based approach.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in VLMs for autonomous driving, one of 9 directions in End-to-end autonomous driving. Builds on 32 of its 47 references that are in the map. First posted on arXiv 22 Mar 2026.

Builds on

32 of 47 references.

References · 32

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2015Fast R-CNNcited by 2,930
  5. 2022Planning-oriented Autonomous Drivingcited by 1,068
  6. 2016End to End Learning for Self-Driving Carscited by 1,000
  7. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  8. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
  9. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  10. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  11. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  12. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 345
20 more
  1. 2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 313
  2. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 233
  3. 2022BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Drivingcited by 191
  4. 2022NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimationcited by 151
  5. 2022Learning from All Vehiclescited by 135
  6. 2020A Survey of End-to-End Driving: Architectures and Training Methodscited by 123
  7. 2021MSeg: A Composite Dataset for Multi-domain Semantic Segmentationcited by 122
  8. 2022ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queriescited by 116
  9. 2017Long-Term On-Board Prediction of People in Traffic Scenes under Uncertaintycited by 63
  10. 2021Stepwise Goal-Driven Networks for Trajectory Predictioncited by 62
  11. 2017Future Person Localization in First-Person Videoscited by 57
  12. 2023VA-DepthNet: A Variational Approach to Single Image Depth Predictioncited by 54
  13. 2020BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimationcited by 47
  14. 2016Joint Attention in Autonomous Driving (JAAD)cited by 35
  15. 2018Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera Systemcited by 34
  16. 2019Efficient Black-box Assessment of Autonomous Vehicle Safetycited by 23
  17. 2018Spatial Uncertainty Sampling for End-to-End Controlcited by 12
  18. 2020Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce Modelcited by 12
  19. 2017End-to-end Learning of Image based Lane-Change Decisioncited by 1
  20. 2017Fast Recurrent Fully Convolutional Networks for Direct Perception in Autonomous Drivingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Real-time Full-stack Traffic Scene Perception for Autonomous Driving with Roadside Cameras
  2. 2022JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes
  3. 2024GaussianAD: Gaussian-Centric End-to-End Autonomous Driving
  4. 2026CooperDrive: Enhancing Driving Decisions Through Cooperative Perception
  5. 2026UniDrive-WM: Unified Understanding, Planning and Generation World Model for Autonomous Driving
  6. 2024XLD: A Cross-Lane Dataset for Benchmarking Novel Driving View Synthesis
  7. 2026UniDrive: A Unified Vision-Language and Grounding Framework for Interpretable Risk Understanding in Autonomous Driving
  8. 2025Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving