mlsanityData to 7 Oct 2026

Surround-view Fisheye Camera Perception for Automated Driving: Overview, Survey and Challenges

arXiv 2205.13281 ↗First posted 26 May 2022cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

Surround-view fisheye cameras are commonly used for near-field sensing in automated driving. Four fisheye cameras on four sides of the vehicle are sufficient to cover 360deg around the vehicle capturing the entire near-field region. Some primary use cases are automated parking, traffic jam assist, and urban driving. There are limited datasets and very little work on near-field perception tasks as the focus in automotive perception is on far-field perception. In contrast to far-field, surround-view perception poses additional challenges due to high precision object detection requirements of 10cm and partial visibility of objects. Due to the large radial distortion of fisheye cameras, standard algorithms cannot be extended easily to the surround-view use case. Thus, we are motivated to provide a self-contained reference for automotive fisheye camera perception for researchers and practitioners. Firstly, we provide a unified and taxonomic treatment of commonly used fisheye camera models. Secondly, we discuss various perception tasks and existing literature. Finally, we discuss the challenges and future direction.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 62 of its 168 references that are in the map. First posted on arXiv 26 May 2022.

Builds on

62 of 168 references.

References · 62

  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  2. 2018YOLOv3: An Incremental Improvementcited by 2,652
  3. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  4. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  5. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  6. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  7. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  8. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  9. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
  10. 2019Omni-Scale Feature Learning for Person Re-Identificationcited by 292
  11. 2017A General and Adaptive Robust Loss Functioncited by 236
  12. 2020Predicting Semantic Map Representations from Images using Pyramid Occupancy Networkscited by 175
38 more
  1. 2019WoodScape: A multi-task, multi-camera fisheye dataset for autonomous drivingcited by 142
  2. 2019Tangent Images for Mitigating Spherical Distortioncited by 79
  3. 2019Spherical CNNs on Unstructured Gridscited by 76
  4. 2018Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Cameracited by 67
  5. 2018DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applicationscited by 61
  6. 2021OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Drivingcited by 57
  7. 2018Kernel Transformer Networks for Compact Spherical Convolutioncited by 56
  8. 2018The Double Sphere Camera Modelcited by 50
  9. 2020SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Drivingcited by 48
  10. 2018Restricted Deformable Convolution based Road Scene Semantic Segmentation Using Surround View Camerascited by 42
  11. 2020Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baselinecited by 41
  12. 2019FisheyeDistanceNet: Self-Supervised Scale-Aware Distance Estimation using Monocular Fisheye Camera for Autonomous Drivingcited by 36
  13. 2020Dynamic Task Weighting Methods for Multi-task Networks in Autonomous Driving Systemscited by 34
  14. 2020UnRectDepthNet: Self-Supervised Monocular Depth Estimation using a Generic Framework for Handling Common Camera Distortion Modelscited by 33
  15. 2022SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Drivingcited by 32
  16. 2018GONet: A Semi-Supervised Deep Learning Approach For Traversability Estimationcited by 28
  17. 2020Universal Semantic Segmentation for Fisheye Urban Driving Imagescited by 25
  18. 2021SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Camerascited by 25
  19. 2016EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras (Extended Abstract)cited by 24
  20. 2021Near-field Perception for Low-Speed Vehicle Automation using Surround-view Fisheye Camerascited by 24
  21. 2019I Can See Clearly Now : Image Restoration via De-Rainingcited by 23
  22. 2019Challenges in Designing Datasets and Validation for Autonomous Drivingcited by 23
  23. 2020Monocular Instance Motion Segmentation for Autonomous Driving: KITTI InstanceMotSeg Dataset and Multi-task Baselinecited by 21
  24. 2018Object Detection in Equirectangular Panoramacited by 20
  25. 2019AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Drivingcited by 19
  26. 2019FisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Drivingcited by 18
  27. 2020TiledSoilingNet: Tile-level Soiling Detection on Automotive Surround-view Cameras Using Coverage Metriccited by 17
  28. 2021BEVDetNet: Bird's Eye View LiDAR Point Cloud based Real-time 3D Object Detection for Autonomous Drivingcited by 17
  29. 2020The NVIDIA PilotNet Experimentscited by 15
  30. 2019SoilingNet: Soiling Detection on Automotive Surround-View Camerascited by 14
  31. 2020Trained Trajectory based Automated Parking System using Visual SLAM on Surround View Camerascited by 14
  32. 2021Adversarial Attacks on Multi-task Visual Perception for Autonomous Drivingcited by 14
  33. 20203D Object Detection from a Single Fisheye Image Without a Single Fisheye Training Imagecited by 13
  34. 2021Adaptable Deformable Convolutions for Semantic Segmentation of Fisheye Images in Autonomous Driving Systemscited by 13
  35. 2019Real-time Joint Object Detection and Semantic Segmentation Network for Automated Drivingcited by 12
  36. 2019NeurAll: Towards a Unified Visual Perception Model for Automated Drivingcited by 11
  37. 2018Real-Time Dense Mapping for Self-driving Vehicles using Fisheye Camerascited by 10
  38. 2018Efficient 2D-3D Matching for Multi-Camera Visual Localizationcited by 10

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 7; 2024: 9; 2025: 6; 2026: 7.

33 papers.

Sort:

By area:

  1. 2022Polar Parametrization for Vision-based Surround-View 3D Detectioncited by 53
  2. 2023F2BEV: Bird's Eye View Generation from Surround-View Fisheye Camera Images for Automated Drivingcited by 12
  3. 2023Optical Flow for Autonomous Driving: Applications, Challenges and Improvementscited by 9
  4. 2026ShareVerse: Multi-Agent Consistent Video Generation for Shared World Modelingcited by 9
  5. 20253DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic Camerascited by 8
  6. 2023FishDreamer: Towards Fisheye Semantic Completion via Unified Image Outpainting and Segmentationcited by 6
  7. 2023Exploiting the Distortion-Semantic Interaction in Fisheye Datacited by 6
  8. 2022Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent Transformercited by 5
  9. 2022Surround-view Fisheye BEV-Perception for Valet Parking: Dataset, Baseline and Distortion-insensitive Multi-task Frameworkcited by 4
  10. 2023Applications of Deep Learning for Top-View Omnidirectional Imaging: A Surveycited by 3
  11. 2023BEVSeg2TP: Surround View Camera Bird's-Eye-View Based Joint Vehicle Segmentation and Ego Vehicle Trajectory Predictioncited by 3
  12. 2024Surround-View Fisheye Optics in Computer Vision and Simulation: Survey and Challengescited by 3
21 more
  1. 2025FishBEV: Distortion-Resilient Bird's Eye View Segmentation with Surround-View Fisheye Camerascited by 3
  2. 2026Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioningcited by 3
  3. 2022Woodscape Fisheye Object Detection for Autonomous Driving -- CVPR 2022 OmniCV Workshop Challengecited by 2
  4. 2024Fisheye Camera and Ultrasonic Sensor Fusion For Near-Field Obstacle Perception in Bird's-Eye-Viewcited by 2
  5. 2024DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird's Eye View Segmentation with Occlusion Reasoningcited by 2
  6. 2024M"obius Transform for Mitigating Perspective Distortions in Representation Learningcited by 2
  7. 2026Benchmarking Multi-View BEV Object Detection with Mixed Pinhole and Fisheye Camerascited by 2
  8. 2024Measuring Natural Scenes SFR of Automotive Fisheye Camerascited by 1
  9. 2024DiffPoint: Single and Multi-view Point Cloud Reconstruction with ViT Based Diffusion Modelcited by 1
  10. 2024FisheyeDetNet: 360deg Surround view Fisheye Camera based Object Detection System for Autonomous Drivingcited by 1
  11. 2025MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single Imagecited by 1
  12. 2025Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Imagescited by 1
  13. 2025FisheyeGaussianLift: BEV Feature Lifting for Surround-View Fisheye Camera Perceptioncited by 1
  14. 2023WoodScape Motion Segmentation for Autonomous Driving -- CVPR 2023 OmniCV Workshop Challengecited by 0
  15. 2024Neural Rendering based Urban Scene Reconstruction for Autonomous Drivingcited by 0
  16. 2024Impact of Video Compression Artifacts on Fisheye Camera Visual Perception Taskscited by 0
  17. 2025Click-Calib: A Robust Extrinsic Calibration Method for Surround-View Systemscited by 0
  18. 2026A 360-degree Multi-camera System for Blue Emergency Light Detection Using Color Attention RT-DETR and the ABLDatasetcited by 0
  19. 2026GazeOnce360: Fisheye-Based 360deg Multi-Person Gaze Estimation with Global-Local Feature Fusioncited by 0
  20. 2026Distortion-Aware PETR for BEV Object Detection with Mixed Pinhole-Fisheye Camerascited by 0
  21. 2026MIVIFI: Bridging Perspective and Fisheye Domains for Training Multi-View Fisheye Image Generation Modelscited by 0