Papers › BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View...
BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation
Cong Pan, Yonghao He, Junran Peng, Qian Zhang, Wei Sui, Zhaoxiang Zhang
Bird's Eye View (BEV) semantic segmentation is a critical task in autonomous driving. However, existing Transformer-based methods confront difficulties in transforming Perspective View (PV) to BEV due to their unidirectional and posterior interaction mechanisms. To address this issue, we propose a novel Bi-directional and Early Interaction Transformers framework named BAEFormer, consisting of (i) an early-interaction PV-BEV pipeline and (ii) a bi-directional cross-attention mechanism. Moreover, we find that the image feature maps' resolution in the cross-attention module has a limited effect on the final performance. Under this critical observation, we propose to enlarge the size of input images and downsample the multi-view image features for cross-interaction, further improving the accuracy while keeping the amount of computation controllable. Our proposed method for BEV semantic segmentation achieves state-of-the-art performance in real-time inference speed on the nuScenes dataset, i.e., 38.9 mIoU at 45 FPS on a single A100 GPU.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Bird's-Eye View Semantic Segmentation | nuScenes | BAEFormer | IoU veh - 224x480 - No vis filter - 100x100 at 0.5 | 36 | #6 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | BAEFormer | IoU veh - 224x480 - Vis filter. - 100x100 at 0.5 | 38.9 | #6 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | BAEFormer | IoU veh - 448x800 - No vis filter - 100x100 at 0.5 | 37.8 | #6 of 17 | Archive leaderboard | report |
| Bird's-Eye View Semantic Segmentation | nuScenes | BAEFormer | IoU veh - 448x800 - Vis filter. - 100x100 at 0.5 | 41.0 | #6 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.
Methods
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