mlsanityData to 14 Oct 2026

PoseDriver: A Unified Approach to Multi-Category Skeleton Detection for Autonomous Driving

arXiv 2603.23215 ↗First posted 24 Mar 2026cs.CV cs.HCcited by 0

Not on the map. Why?

Abstract (arXiv)

Object skeletons offer a concise representation of structural information, capturing essential aspects of posture and orientation that are crucial for autonomous driving applications. However, a unified architecture that simultaneously handles multiple instances and categories using only the input image remains elusive. In this paper, we introduce PoseDriver, a unified framework for bottom-up multi-category skeleton detection tailored to common objects in driving scenarios. We model each category as a distinct task to systematically address the challenges of multi-task learning. Specifically, we propose a novel approach for lane detection based on skeleton representations, achieving state-of-the-art performance on the OpenLane dataset. Moreover, we present a new dataset for bicycle skeleton detection and assess the transferability of our framework to novel categories. Experimental results validate the effectiveness of the proposed approach.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 48 of its 68 references that are in the map. First posted on arXiv 24 Mar 2026.

Builds on

48 of 68 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2017Mask R-CNNcited by 7,277
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  6. 2022A ConvNet for the 2020scited by 3,579
  7. 2017Decoupled Weight Decay Regularizationcited by 1,831
  8. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  9. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  10. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  11. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  12. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 456
36 more
  1. 2016Convolutional Pose Machinescited by 325
  2. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 212
  3. 2019Domain-Specific Batch Normalization for Unsupervised Domain Adaptationcited by 197
  4. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 193
  5. 2017Spatial As Deep: Spatial CNN for Traffic Scene Understandingcited by 187
  6. 2019Learning Lightweight Lane Detection CNNs by Self Attention Distillationcited by 162
  7. 2024GenAD: Generalized Predictive Model for Autonomous Drivingcited by 150
  8. 2022PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmarkcited by 140
  9. 2020Keep your Eyes on the Lane: Real-time Attention-guided Lane Detectioncited by 138
  10. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  11. 2018Towards End-to-End Lane Detection: an Instance Segmentation Approachcited by 129
  12. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  13. 2020End-to-end Lane Shape Prediction with Transformerscited by 111
  14. 2019Cross-Domain Adaptation for Animal Pose Estimationcited by 108
  15. 2020PolyLaneNet: Lane Estimation via Deep Polynomial Regressioncited by 95
  16. 2021CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolutioncited by 95
  17. 2022Rethinking Efficient Lane Detection via Curve Modelingcited by 88
  18. 2022CLRNet: Cross Layer Refinement Network for Lane Detectioncited by 82
  19. 2020CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blendingcited by 80
  20. 2020RESA: Recurrent Feature-Shift Aggregator for Lane Detectioncited by 77
  21. 2022A Keypoint-based Global Association Network for Lane Detectioncited by 68
  22. 2021Focus on Local: Detecting Lane Marker from Bottom Up via Key Pointcited by 65
  23. 2018ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Drivingcited by 59
  24. 2021OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Associationcited by 55
  25. 2019MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimationcited by 39
  26. 2021Polarized Self-Attention: Towards High-quality Pixel-wise Regressioncited by 39
  27. 2022SuperAnimal pretrained pose estimation models for behavioral analysiscited by 39
  28. 2022Pose for Everything: Towards Category-Agnostic Pose Estimationcited by 36
  29. 2023On the Benefits of 3D Pose and Tracking for Human Action Recognitioncited by 32
  30. 2023X-Pose: Detecting Any Keypointscited by 21
  31. 2022RCLane: Relay Chain Prediction for Lane Detectioncited by 20
  32. 2021A Novel Dataset for Keypoint Detection of quadruped Animals from Imagescited by 19
  33. 2023CLRerNet: Improving Confidence of Lane Detection with LaneIoUcited by 17
  34. 2024Advanced computer vision for extracting georeferenced vehicle trajectories from drone imagerycited by 11
  35. 2021A context-aware pedestrian trajectory prediction framework for automated vehiclescited by 10
  36. 2024Context-aware Multi-task Learning for Pedestrian Intent and Trajectory Predictioncited by 3

Built on by

Not cited yet.