mlsanityData to 14 Oct 2026

SoK: Vehicle Orientation Representations for Deep Rotation Estimation

arXiv 2112.04421 ↗First posted 8 Dec 2021cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

In recent years, there is an influx of deep learning models for 3D vehicle object detection. However, little attention was paid to orientation prediction. Existing research work proposed various vehicle orientation representation methods for deep learning, however a holistic, systematic review has not been conducted. Through our experiments, we categorize and compare the accuracy performance of various existing orientation representations using the KITTI 3D object detection dataset, and propose a new form of orientation representation: Tricosine. Among these, the 2D Cartesian-based representation, or Single Bin, achieves the highest accuracy, with additional channeled inputs (positional encoding and depth map) not boosting prediction performance. Our code is published on GitHub: https://github.com/umd-fire-coml/KITTI-orientation-learning

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 78 of its 98 references that are in the map. First posted on arXiv 8 Dec 2021.

Builds on

78 of 98 references.

References · 78

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  7. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  8. 2019Objects as Pointscited by 1,175
  9. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  10. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  11. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  12. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
38 more
  1. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 447
  2. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 410
  3. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  4. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 327
  5. 20163D Bounding Box Estimation Using Deep Learning and Geometrycited by 278
  6. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 249
  7. 2019Disentangling Monocular 3D Object Detectioncited by 217
  8. 2020SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimationcited by 204
  9. 2020Multi-Task Multi-Sensor Fusion for 3D Object Detectioncited by 203
  10. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 202
  11. 2020Rethinking Positional Encoding in Language Pre-trainingcited by 197
  12. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
  13. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  14. 2019MVX-Net: Multimodal VoxelNet for 3D Object Detectioncited by 163
  15. 2020Rethinking Transformer-based Set Prediction for Object Detectioncited by 156
  16. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 156
  17. 2020MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationshipscited by 153
  18. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 140
  19. 2019Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Drivingcited by 137
  20. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  21. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  22. 2019GS3D: An Efficient 3D Object Detection Framework for Autonomous Drivingcited by 106
  23. 2019Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstructioncited by 106
  24. 2017Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular imagecited by 95
  25. 2021Learnable Fourier Features for Multi-Dimensional Spatial Positional Encodingcited by 93
  26. 2021AutoShape: Real-Time Shape-Aware Monocular 3D Object Detectioncited by 87
  27. 2021Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detectioncited by 84
  28. 2021Geometry-based Distance Decomposition for Monocular 3D Object Detectioncited by 84
  29. 2021MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagationcited by 82
  30. 2020JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detectioncited by 79
  31. 2020HDNET: Exploiting HD Maps for 3D Object Detectioncited by 78
  32. 2018Benchmark Analysis of Representative Deep Neural Network Architecturescited by 77
  33. 2018Joint Monocular 3D Vehicle Detection and Trackingcited by 77
  34. 2021Monocular 3D Object Detection: An Extrinsic Parameter Free Approachcited by 69
  35. 2019Deep Fitting Degree Scoring Network for Monocular 3D Object Detectioncited by 67
  36. 2021Ground-aware Monocular 3D Object Detection for Autonomous Drivingcited by 65
  37. 2021Progressive Coordinate Transforms for Monocular 3D Object Detectioncited by 52
  38. 2020Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimationcited by 43

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66