F2BEV: Bird's Eye View Generation from Surround-View Fisheye Camera Images for Automated Driving
Not on the map. Why?
Abstract (arXiv)
Bird's Eye View (BEV) representations are tremendously useful for perception-related automated driving tasks. However, generating BEVs from surround-view fisheye camera images is challenging due to the strong distortions introduced by such wide-angle lenses. We take the first step in addressing this challenge and introduce a baseline, F2BEV, to generate discretized BEV height maps and BEV semantic segmentation maps from fisheye images. F2BEV consists of a distortion-aware spatial cross attention module for querying and consolidating spatial information from fisheye image features in a transformer-style architecture followed by a task-specific head. We evaluate single-task and multi-task variants of F2BEV on our synthetic FB-SSEM dataset, all of which generate better BEV height and segmentation maps (in terms of the IoU) than a state-of-the-art BEV generation method operating on undistorted fisheye images. We also demonstrate discretized height map generation from real-world fisheye images using F2BEV. Our dataset is publicly available at https://github.com/volvo-cars/FB-SSEM-dataset
Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 33 of its 45 references that are in the map. First posted on arXiv 7 Mar 2023.
Builds on
33 of 45 references.
References · 33
- 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
- 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
- 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
- 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
- 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 575
- 2015A Neural Algorithm of Artistic Stylecited by 483
- 2021FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Camerascited by 239
- 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
- 2020Predicting Semantic Map Representations from Images using Pyramid Occupancy Networkscited by 175
- 2019Cross-view Semantic Segmentation for Sensing Surroundingscited by 174
- 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
- 2019WoodScape: A multi-task, multi-camera fisheye dataset for autonomous drivingcited by 144
21 more
- 2022Vision-Centric BEV Perception: A Surveycited by 126
- 2022BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigscited by 123
- 2021Translating Images into Mapscited by 115
- 2021Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformerscited by 109
- 2018Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networkscited by 84
- 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 72
- 2018The Double Sphere Camera Modelcited by 52
- 2022Learning Ego 3D Representation as Ray Tracingcited by 43
- 2018Restricted Deformable Convolution based Road Scene Semantic Segmentation Using Surround View Camerascited by 42
- 2020Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baselinecited by 42
- 2022Surround-view Fisheye Camera Perception for Automated Driving: Overview, Survey and Challengescited by 34
- 2020UnRectDepthNet: Self-Supervised Monocular Depth Estimation using a Generic Framework for Handling Common Camera Distortion Modelscited by 33
- 2022SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Drivingcited by 32
- 2022CC-3DT: Panoramic 3D Object Tracking via Cross-Camera Fusioncited by 31
- 2018Generative Adversarial Frontal View to Bird View Synthesiscited by 25
- 2020Universal Semantic Segmentation for Fisheye Urban Driving Imagescited by 25
- 2021SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Camerascited by 25
- 2022GitNet: Geometric Prior-based Transformation for Birds-Eye-View Segmentationcited by 24
- 2019OmniMVS: End-to-End Learning for Omnidirectional Stereo Matchingcited by 21
- 2018The Right (Angled) Perspective: Improving the Understanding of Road Scenes Using Boosted Inverse Perspective Mappingcited by 11
- 2021Vision-based Driver Assistance Systems: Survey, Taxonomy and Advancescited by 10
Built on by
Citing papers per year: 2024: 3; 2025: 3; 2026: 6.
12 papers.
- 2025Dur360BEV: A Real-world 360-degree Single Camera Dataset and Benchmark for Bird-Eye View Mapping in Autonomous Drivingcited by 5
- 2026Panoramic Multimodal Semantic Occupancy Prediction for Quadruped Robotscited by 5
- 2024Enhanced Parking Perception by Multi-Task Fisheye Cross-view Transformerscited by 4
- 2024Surround-View Fisheye Optics in Computer Vision and Simulation: Survey and Challengescited by 3
- 2025FishBEV: Distortion-Resilient Bird's Eye View Segmentation with Surround-View Fisheye Camerascited by 3
- 2026FishRoPE: Projective Rotary Position Embeddings for Omnidirectional Visual Perceptioncited by 3
- 2024DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird's Eye View Segmentation with Occlusion Reasoningcited by 2
- 2026O3N: Omnidirectional Open-Vocabulary Occupancy Prediction for Embodied Intelligent Roboticscited by 2
- 2026Benchmarking Multi-View BEV Object Detection with Mixed Pinhole and Fisheye Camerascited by 2
- 2025Exploring Surround-View Fisheye Camera 3D Object Detectioncited by 1
- 2026Distortion-Aware PETR for BEV Object Detection with Mixed Pinhole-Fisheye Camerascited by 0
- 2026Geometry-Aware Fisheye-LiDAR Fusion for Robust 3D Object Detection in Low-Overlap Setupscited by 0
- 2026Geometry-Aware Fisheye-LiDAR Fusion for Robust 3D Object Detection in Low-Overlap Setups7 Jun 2026
- 2026Distortion-Aware PETR for BEV Object Detection with Mixed Pinhole-Fisheye Cameras7 Jun 2026
- 2026FishRoPE: Projective Rotary Position Embeddings for Omnidirectional Visual Perception12 Apr 2026
- 2026Benchmarking Multi-View BEV Object Detection with Mixed Pinhole and Fisheye Cameras29 Mar 2026
- 2026Panoramic Multimodal Semantic Occupancy Prediction for Quadruped Robots13 Mar 2026
- 2026O3N: Omnidirectional Open-Vocabulary Occupancy Prediction for Embodied Intelligent Robotics12 Mar 2026
- 2025Exploring Surround-View Fisheye Camera 3D Object Detection24 Nov 2025
- 2025FishBEV: Distortion-Resilient Bird's Eye View Segmentation with Surround-View Fisheye Cameras17 Sep 2025
- 2025Dur360BEV: A Real-world 360-degree Single Camera Dataset and Benchmark for Bird-Eye View Mapping in Autonomous Driving2 Mar 2025
- 2024Enhanced Parking Perception by Multi-Task Fisheye Cross-view Transformers22 Aug 2024
- 2024DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird's Eye View Segmentation with Occlusion Reasoning9 Apr 2024
- 2024Surround-View Fisheye Optics in Computer Vision and Simulation: Survey and Challenges19 Feb 2024