Papers › Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?
Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?
Adam W. Harley, Zhaoyuan Fang, Jie Li, Rares Ambrus, Katerina Fragkiadaki
Building 3D perception systems for autonomous vehicles that do not rely on high-density LiDAR is a critical research problem because of the expense of LiDAR systems compared to cameras and other sensors. Recent research has developed a variety of camera-only methods, where features are differentiably "lifted" from the multi-camera images onto the 2D ground plane, yielding a "bird's eye view" (BEV) feature representation of the 3D space around the vehicle. This line of work has produced a variety of novel "lifting" methods, but we observe that other details in the training setups have shifted at the same time, making it unclear what really matters in top-performing methods. We also observe that using cameras alone is not a real-world constraint, considering that additional sensors like radar have been integrated into real vehicles for years already. In this paper, we first of all attempt to elucidate the high-impact factors in the design and training protocol of BEV perception models. We find that batch size and input resolution greatly affect performance, while lifting strategies have a more modest effect -- even a simple parameter-free lifter works well. Second, we demonstrate that radar data can provide a substantial boost to performance, helping to close the gap between camera-only and LiDAR-enabled systems. We analyze the radar usage details that lead to good performance, and invite the community to re-consider this commonly-neglected part of the sensor platform.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Bird's-Eye View Semantic Segmentation | Lyft Level 5 | Simple-BEV (EfficientNet-b4) | IoU vehicle - 224x480 - Long | 44.5 | #3 of 7 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | Lyft Level 5 | Simple-BEV (EfficientNet-b4) | IoU vehicle - 224x480 - Short | 70.4 | #3 of 7 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | Lyft Level 5 | Simple-BEV (ResNet-50) | IoU vehicle - 224x480 - Long | 43.6 | #5 of 7 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | Lyft Level 5 | Simple-BEV (ResNet-50) | IoU vehicle - 224x480 - Short | 70.7 | #5 of 7 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | Simple-BEV | IoU veh - 224x480 - No vis filter - 100x100 at 0.5 | 36.9 | #3 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | Simple-BEV | IoU veh - 224x480 - Vis filter. - 100x100 at 0.5 | 43.0 | #3 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | Simple-BEV | IoU veh - 448x800 - No vis filter - 100x100 at 0.5 | 40.9 | #3 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | Simple-BEV | IoU veh - 448x800 - Vis filter. - 100x100 at 0.5 | 46.6 | #3 of 17 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections