Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2205.13542 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913487196782592 |
|---|---|
| author | Liu, Zhijian Tang, Haotian Amini, Alexander Yang, Xinyu Mao, Huizi Rus, Daniela Han, Song |
| author_facet | Liu, Zhijian Tang, Haotian Amini, Alexander Yang, Xinyu Mao, Huizi Rus, Daniela Han, Song |
| contents | Multi-sensor fusion is essential for an accurate and reliable autonomous driving system. Recent approaches are based on point-level fusion: augmenting the LiDAR point cloud with camera features. However, the camera-to-LiDAR projection throws away the semantic density of camera features, hindering the effectiveness of such methods, especially for semantic-oriented tasks (such as 3D scene segmentation). In this paper, we break this deeply-rooted convention with BEVFusion, an efficient and generic multi-task multi-sensor fusion framework. It unifies multi-modal features in the shared bird's-eye view (BEV) representation space, which nicely preserves both geometric and semantic information. To achieve this, we diagnose and lift key efficiency bottlenecks in the view transformation with optimized BEV pooling, reducing latency by more than 40x. BEVFusion is fundamentally task-agnostic and seamlessly supports different 3D perception tasks with almost no architectural changes. It establishes the new state of the art on nuScenes, achieving 1.3% higher mAP and NDS on 3D object detection and 13.6% higher mIoU on BEV map segmentation, with 1.9x lower computation cost. Code to reproduce our results is available at https://github.com/mit-han-lab/bevfusion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2205_13542 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation Liu, Zhijian Tang, Haotian Amini, Alexander Yang, Xinyu Mao, Huizi Rus, Daniela Han, Song Computer Vision and Pattern Recognition Multi-sensor fusion is essential for an accurate and reliable autonomous driving system. Recent approaches are based on point-level fusion: augmenting the LiDAR point cloud with camera features. However, the camera-to-LiDAR projection throws away the semantic density of camera features, hindering the effectiveness of such methods, especially for semantic-oriented tasks (such as 3D scene segmentation). In this paper, we break this deeply-rooted convention with BEVFusion, an efficient and generic multi-task multi-sensor fusion framework. It unifies multi-modal features in the shared bird's-eye view (BEV) representation space, which nicely preserves both geometric and semantic information. To achieve this, we diagnose and lift key efficiency bottlenecks in the view transformation with optimized BEV pooling, reducing latency by more than 40x. BEVFusion is fundamentally task-agnostic and seamlessly supports different 3D perception tasks with almost no architectural changes. It establishes the new state of the art on nuScenes, achieving 1.3% higher mAP and NDS on 3D object detection and 13.6% higher mIoU on BEV map segmentation, with 1.9x lower computation cost. Code to reproduce our results is available at https://github.com/mit-han-lab/bevfusion. |
| title | BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2205.13542 |