mlsanityData to 7 Oct 2026

Vision-based Uneven BEV Representation Learning with Polar Rasterization and Surface Estimation

arXiv 2207.01878 ↗First posted 5 Jul 2022cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

In this work, we propose PolarBEV for vision-based uneven BEV representation learning. To adapt to the foreshortening effect of camera imaging, we rasterize the BEV space both angularly and radially, and introduce polar embedding decomposition to model the associations among polar grids. Polar grids are rearranged to an array-like regular representation for efficient processing. Besides, to determine the 2D-to-3D correspondence, we iteratively update the BEV surface based on a hypothetical plane, and adopt height-based feature transformation. PolarBEV keeps real-time inference speed on a single 2080Ti GPU, and outperforms other methods for both BEV semantic segmentation and BEV instance segmentation. Thorough ablations are presented to validate the design. The code will be released at urlhttps://github.com/SuperZ-Liu/PolarBEV.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 26 of its 34 references that are in the map. First posted on arXiv 5 Jul 2022.

Builds on

26 of 34 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  5. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  6. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  7. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  8. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  9. 2021FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Camerascited by 239
  10. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 201
  11. 2020Predicting Semantic Map Representations from Images using Pyramid Occupancy Networkscited by 175
  12. 2019Cross-view Semantic Segmentation for Sensing Surroundingscited by 173
14 more
  1. 2021Translating Images into Mapscited by 115
  2. 2020Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentationcited by 112
  3. 2021Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Imagescited by 98
  4. 2018Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networkscited by 84
  5. 2022Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformercited by 80
  6. 2020A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird's Eye Viewcited by 71
  7. 2022Polar Parametrization for Vision-based Surround-View 3D Detectioncited by 53
  8. 2018Learning to Look around Objects for Top-View Representations of Outdoor Scenescited by 37
  9. 2019A Geometric Approach to Obtain a Bird's Eye View from an Imagecited by 34
  10. 2020Driving among Flatmobiles: Bird-Eye-View occupancy grids from a monocular camera for holistic trajectory planningcited by 24
  11. 2018A Parametric Top-View Representation of Complex Road Scenescited by 20
  12. 2020Understanding Road Layout from Videos as a Wholecited by 10
  13. 2022AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perceptioncited by 5
  14. 2022"The Pedestrian next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mappingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 10; 2024: 5; 2025: 5; 2026: 1.

23 papers.

Sort:

By area:

  1. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 613
  2. 2022MapTR: Structured Modeling and Learning for Online Vectorized HD Map Constructioncited by 311
  3. 2023MapTRv2: An End-to-End Framework for Online Vectorized HD Map Constructioncited by 192
  4. 2023Symphonize 3D Semantic Scene Completion with Contextual Instance Queriescited by 88
  5. 2023Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Constructioncited by 50
  6. 2023PPAD: Iterative Interactions of Prediction and Planning for End-to-end Autonomous Drivingcited by 33
  7. 2022Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Predictioncited by 28
  8. 2023Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Reviewcited by 25
  9. 2023LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillationcited by 18
  10. 2024ADMap: Anti-disturbance framework for reconstructing online vectorized HD mapcited by 14
  11. 2023VMA: Divide-and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scenecited by 9
  12. 2024RayFormer: Improving Query-Based Multi-Camera 3D Object Detection via Ray-Centric Strategiescited by 9
11 more
  1. 2023Semi-Supervised Learning for Visual Bird's Eye View Semantic Segmentationcited by 8
  2. 2025InteractionMap: Improving Online Vectorized HDMap Construction with Interactioncited by 8
  3. 2025Spatial Retrieval Augmented Autonomous Drivingcited by 5
  4. 2024Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detectioncited by 4
  5. 2023One Training for Multiple Deployments: Polar-based Adaptive BEV Perception for Autonomous Drivingcited by 3
  6. 2024PolarBEVDet: Exploring Polar Representation for Multi-View 3D Object Detection in Bird's-Eye-Viewcited by 3
  7. 2025Echo Planning for Autonomous Driving: From Current Observations to Future Trajectories and Backcited by 3
  8. 2025SynAD: Enhancing Real-World End-to-End Autonomous Driving Models through Synthetic Data Integrationcited by 3
  9. 2024PetalView: Fine-grained Location and Orientation Extraction of Street-view Images via Cross-view Local Search with Supplementary Materialscited by 1
  10. 2025SPHERE: Semantic-PHysical Engaged REpresentation for 3D Semantic Scene Completioncited by 1
  11. 2026Multi-Resolution Alignment for Voxel Sparsity in Camera-Based 3D Semantic Scene Completioncited by 0