Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929429682323456 |
|---|---|
| author | Chen, Zhili Xu, Shuangjie Ye, Maosheng Qian, Zian Zou, Xiaoyi Yeung, Dit-Yan Chen, Qifeng |
| author_facet | Chen, Zhili Xu, Shuangjie Ye, Maosheng Qian, Zian Zou, Xiaoyi Yeung, Dit-Yan Chen, Qifeng |
| contents | The Bird's-Eye-View (BEV) representation is a critical factor that directly impacts the 3D object detection performance, but the traditional BEV grid representation induces quadratic computational cost as the spatial resolution grows. To address this limitation, we present a new camera-based 3D object detector with high-resolution vector representation: VectorFormer. The presented high-resolution vector representation is combined with the lower-resolution BEV representation to efficiently exploit 3D geometry from multi-camera images at a high resolution through our two novel modules: vector scattering and gathering. To this end, the learned vector representation with richer scene contexts can serve as the decoding query for final predictions. We conduct extensive experiments on the nuScenes dataset and demonstrate state-of-the-art performance in NDS and inference time. Furthermore, we investigate query-BEV-based methods incorporated with our proposed vector representation and observe a consistent performance improvement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15354 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detection Chen, Zhili Xu, Shuangjie Ye, Maosheng Qian, Zian Zou, Xiaoyi Yeung, Dit-Yan Chen, Qifeng Computer Vision and Pattern Recognition Robotics The Bird's-Eye-View (BEV) representation is a critical factor that directly impacts the 3D object detection performance, but the traditional BEV grid representation induces quadratic computational cost as the spatial resolution grows. To address this limitation, we present a new camera-based 3D object detector with high-resolution vector representation: VectorFormer. The presented high-resolution vector representation is combined with the lower-resolution BEV representation to efficiently exploit 3D geometry from multi-camera images at a high resolution through our two novel modules: vector scattering and gathering. To this end, the learned vector representation with richer scene contexts can serve as the decoding query for final predictions. We conduct extensive experiments on the nuScenes dataset and demonstrate state-of-the-art performance in NDS and inference time. Furthermore, we investigate query-BEV-based methods incorporated with our proposed vector representation and observe a consistent performance improvement. |
| title | Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detection |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2407.15354 |