mlsanityData to 7 Oct 2026

PVP: Polar Representation Boost for 3D Semantic Occupancy Prediction

arXiv 2412.07616 ↗First posted 10 Dec 2024cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Recently, polar coordinate-based representations have shown promise for 3D perceptual tasks. Compared to Cartesian methods, polar grids provide a viable alternative, offering better detail preservation in nearby spaces while covering larger areas. However, they face feature distortion due to non-uniform division. To address these issues, we introduce the Polar Voxel Occupancy Predictor (PVP), a novel 3D multi-modal predictor that operates in polar coordinates. PVP features two key design elements to overcome distortion: a Global Represent Propagation (GRP) module that integrates global spatial data into 3D volumes, and a Plane Decomposed Convolution (PD-Conv) that simplifies 3D distortions into 2D convolutions. These innovations enable PVP to outperform existing methods, achieving significant improvements in mIoU and IoU metrics on the OpenOccupancy dataset.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 34 of its 43 references that are in the map. First posted on arXiv 10 Dec 2024.

Builds on

34 of 43 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  6. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  7. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  8. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  9. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  10. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  11. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  12. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
22 more
  1. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  2. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 287
  3. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  4. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 222
  5. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 218
  6. 20203D Object Detection with Pointformercited by 194
  7. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  8. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  9. 2022Understanding The Robustness in Vision Transformerscited by 144
  10. 2020Anisotropic Convolutional Networks for 3D Semantic Scene Completioncited by 126
  11. 20203D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Priorcited by 124
  12. 2023MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Drivingcited by 68
  13. 2022CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformercited by 66
  14. 2021SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networkscited by 59
  15. 2023PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Predictioncited by 51
  16. 2021LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentationcited by 34
  17. 2023SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detectioncited by 14
  18. 2023Scalable Geometric Fracture Assembly via Co-creation Space among Assemblerscited by 13
  19. 2023PARTNER: Level up the Polar Representation for LiDAR 3D Object Detectioncited by 9
  20. 2022AI-enabled Automatic Multimodal Fusion of Cone-Beam CT and Intraoral Scans for Intelligent 3D Tooth-Bone Reconstruction and Clinical Applicationscited by 3
  21. 2023One Training for Multiple Deployments: Polar-based Adaptive BEV Perception for Autonomous Drivingcited by 3
  22. 2023ToothSegNet: Image Degradation meets Tooth Segmentation in CBCT Imagescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026AquaBEV: Monocular Underwater BEV Occupancy with 3D Sonar Supervisioncited by 1
  2. 2026AquaBEV-Nav: Learned BEV Occupancy for Underwater Navigation and Explorationcited by 0