A BEV-Fusion Based Framework for Sequential Multi-Modal Beam Prediction in mmWave Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908942413594624 |
|---|---|
| author | Zeng, Jiaming Pan, Cunhua Weng, Haoyang Liu, Ruijing Ren, Hong Wang, Jiangzhou |
| author_facet | Zeng, Jiaming Pan, Cunhua Weng, Haoyang Liu, Ruijing Ren, Hong Wang, Jiangzhou |
| contents | Beam prediction is critical for reducing beam-training overhead in millimeter-wave (mmWave) systems, especially in high-mobility vehicular scenarios. This paper presents a BEV-Fusion based framework that unifies camera, LiDAR, radar, and GPS modalities in a shared bird's-eye-view (BEV) representation for spatially consistent multi-modal fusion. Unlike priorapproaches that fuse globally pooled one-dimensional features, the proposed method performs fusion in BEV space to preservecross-modal geometric structure and visual semantic density. A learned camera-to-BEV module based on cross-attention is adopted to generate BEV-aligned visual features without relying on precise camera calibration, and a temporal transformer is used to aggregate five-step sequential observations for motion-aware beam prediction. Experiments on the DeepSense 6G benchmark show that BEV-Fusion achieves approximately 87% distance- based accuracy (DBA) on scenarios 32, 33 and 34, outperforming the TransFuser baseline. These results indicate that BEV-space fusion provides an effective spatial abstraction for sensing-assisted beam prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_05668 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A BEV-Fusion Based Framework for Sequential Multi-Modal Beam Prediction in mmWave Systems Zeng, Jiaming Pan, Cunhua Weng, Haoyang Liu, Ruijing Ren, Hong Wang, Jiangzhou Signal Processing Beam prediction is critical for reducing beam-training overhead in millimeter-wave (mmWave) systems, especially in high-mobility vehicular scenarios. This paper presents a BEV-Fusion based framework that unifies camera, LiDAR, radar, and GPS modalities in a shared bird's-eye-view (BEV) representation for spatially consistent multi-modal fusion. Unlike priorapproaches that fuse globally pooled one-dimensional features, the proposed method performs fusion in BEV space to preservecross-modal geometric structure and visual semantic density. A learned camera-to-BEV module based on cross-attention is adopted to generate BEV-aligned visual features without relying on precise camera calibration, and a temporal transformer is used to aggregate five-step sequential observations for motion-aware beam prediction. Experiments on the DeepSense 6G benchmark show that BEV-Fusion achieves approximately 87% distance- based accuracy (DBA) on scenarios 32, 33 and 34, outperforming the TransFuser baseline. These results indicate that BEV-space fusion provides an effective spatial abstraction for sensing-assisted beam prediction. |
| title | A BEV-Fusion Based Framework for Sequential Multi-Modal Beam Prediction in mmWave Systems |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2604.05668 |