Papers › PointBeV: A Sparse Approach to BeV Predictions
PointBeV: A Sparse Approach to BeV Predictions
Loick Chambon, Eloi Zablocki, Mickael Chen, Florent Bartoccioni, Patrick Perez, Matthieu Cord
Bird's-eye View (BeV) representations have emerged as the de-facto shared space in driving applications, offering a unified space for sensor data fusion and supporting various downstream tasks. However, conventional models use grids with fixed resolution and range and face computational inefficiencies due to the uniform allocation of resources across all cells. To address this, we propose PointBeV, a novel sparse BeV segmentation model operating on sparse BeV cells instead of dense grids. This approach offers precise control over memory usage, enabling the use of long temporal contexts and accommodating memory-constrained platforms. PointBeV employs an efficient two-pass strategy for training, enabling focused computation on regions of interest. At inference time, it can be used with various memory/performance trade-offs and flexibly adjusts to new specific use cases. PointBeV achieves state-of-the-art results on the nuScenes dataset for vehicle, pedestrian, and lane segmentation, showcasing superior performance in static and temporal settings despite being trained solely with sparse signals. We will release our code along with two new efficient modules used in the architecture: Sparse Feature Pulling, designed for the effective extraction of features from images to BeV, and Submanifold Attention, which enables efficient temporal modeling. Our code is available at https://github.com/valeoai/PointBeV.
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 | PointBeV (EfficientNet-b4) | IoU vehicle - 224x480 - Long | 45.4 | #1 of 7 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | Lyft Level 5 | PointBeV (EfficientNet-b4) | IoU vehicle - 224x480 - Short | 72.6 | #1 of 7 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | Lyft Level 5 | PointBeV (ResNet-50) | IoU vehicle - 224x480 - Long | 44.5 | #2 of 7 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | Lyft Level 5 | PointBeV (ResNet-50) | IoU vehicle - 224x480 - Short | 72.3 | #2 of 7 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | PointBeV | IoU ped - 224x480 - Vis filter. - 100x100 at 0.5 | 19.9 | #1 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | PointBeV | IoU veh - 224x480 - No vis filter - 100x100 at 0.5 | 39.9 | #1 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | PointBeV | IoU veh - 224x480 - Vis filter. - 100x100 at 0.5 | 44.7 | #1 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | PointBeV | IoU veh - 448x800 - No vis filter - 100x100 at 0.5 | 43.2 | #1 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | PointBeV | IoU veh - 448x800 - Vis filter. - 100x100 at 0.5 | 48.7 | #1 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | PointBeV (static) | IoU lane - 224x480 - 100x100 at 0.5 | 49.6 | #2 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | PointBeV (static) | IoU ped - 224x480 - Vis filter. - 100x100 at 0.5 | 18.5 | #2 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | PointBeV (static) | IoU veh - 224x480 - No vis filter - 100x100 at 0.5 | 38.7 | #2 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | PointBeV (static) | IoU veh - 224x480 - Vis filter. - 100x100 at 0.5 | 44.0 | #2 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | PointBeV (static) | IoU veh - 448x800 - No vis filter - 100x100 at 0.5 | 42.1 | #2 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | PointBeV (static) | IoU veh - 448x800 - Vis filter. - 100x100 at 0.5 | 47.6 | #2 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