mlsanityData to 14 Oct 2026

Omnidirectional Depth-Aided Occupancy Prediction based on Cylindrical Voxel for Autonomous Driving

arXiv 2504.01023 ↗First posted 26 Mar 2025cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurate 3D perception is essential for autonomous driving. Traditional methods often struggle with geometric ambiguity due to a lack of geometric prior. To address these challenges, we use omnidirectional depth estimation to introduce geometric prior. Based on the depth information, we propose a Sketch-Coloring framework OmniDepth-Occ. Additionally, our approach introduces a cylindrical voxel representation based on polar coordinate to better align with the radial nature of panoramic camera views. To address the lack of fisheye camera dataset in autonomous driving tasks, we also build a virtual scene dataset with six fisheye cameras, and the data volume has reached twice that of SemanticKITTI. Experimental results demonstrate that our Sketch-Coloring network significantly enhances 3D perception performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 39 of its 42 references that are in the map. First posted on arXiv 26 Mar 2025.

Builds on

39 of 42 references.

References · 39

  1. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  2. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  3. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  4. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  5. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  6. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  7. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  8. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  9. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  10. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 389
  11. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  12. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 352
27 more
  1. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 341
  2. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 332
  3. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 316
  4. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 313
  5. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  6. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 293
  7. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 275
  8. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  9. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 223
  10. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 221
  11. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 188
  12. 2020Predicting Semantic Map Representations from Images using Pyramid Occupancy Networkscited by 175
  13. 2023FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformationcited by 165
  14. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  15. 2023RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervisioncited by 128
  16. 2022BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigscited by 123
  17. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  18. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 115
  19. 2023COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Predictioncited by 96
  20. 2023Symphonize 3D Semantic Scene Completion with Contextual Instance Queriescited by 90
  21. 2020Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detectioncited by 78
  22. 2022Polar Parametrization for Vision-based Surround-View 3D Detectioncited by 53
  23. 2023PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Predictioncited by 52
  24. 2023Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applicationscited by 52
  25. 2021Paris-CARLA-3D: A Real and Synthetic Outdoor Point Cloud Dataset for Challenging Tasks in 3D Mappingcited by 25
  26. 2024OccFlowNet: Towards Self-supervised Occupancy Estimation via Differentiable Rendering and Occupancy Flowcited by 22
  27. 2023Multi-Scale Occ: 4th Place Solution for CVPR 2023 3D Occupancy Prediction Challengecited by 7

Built on by

Not cited yet.