Details
| Original language | English |
|---|---|
| Title of host publication | 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
| Pages | 22296-22305 |
| Number of pages | 10 |
| ISBN (electronic) | 979-8-3315-4365-5 |
| Publication status | Published - 10 Jun 2025 |
Publication series
| Name | CVPR |
|---|---|
| ISSN (electronic) | 2575-7075 |
Abstract
Keywords
- cs.CV, data fusion, cooperative perception, point cloud, autonomous driving
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Computer Science(all)
- Computer Vision and Pattern Recognition
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2025. p. 22296-22305 (CVPR).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - SparseAlign
T2 - A Fully Sparse Framework for Cooperative Object Detection
AU - Yuan, Yunshuang
AU - Xia, Yan
AU - Cremers, Daniel
AU - Sester, Monika
N1 - Publisher Copyright: © 2025 IEEE.
PY - 2025/6/10
Y1 - 2025/6/10
N2 - Cooperative perception can increase the view field and decrease the occlusion of an ego vehicle, hence improving the perception performance and safety of autonomous driving. Despite the success of previous works on cooperative object detection, they mostly operate on dense Bird's Eye View (BEV) feature maps, which are computationally demanding and can hardly be extended to long-range detection problems. More efficient fully sparse frameworks are rarely explored. In this work, we design a fully sparse framework, SparseAlign, with three key features: an enhanced sparse 3D backbone, a query-based temporal context learning module, and a robust detection head specially tailored for sparse features. Extensive experimental results on both OPV2V and DairV2X datasets show that our framework, despite its sparsity, outperforms the state of the art with less communication bandwidth requirements. In addition, experiments on the OPV2Vt and DairV2Xt datasets for time-aligned cooperative object detection also show a significant performance gain compared to the baseline works.
AB - Cooperative perception can increase the view field and decrease the occlusion of an ego vehicle, hence improving the perception performance and safety of autonomous driving. Despite the success of previous works on cooperative object detection, they mostly operate on dense Bird's Eye View (BEV) feature maps, which are computationally demanding and can hardly be extended to long-range detection problems. More efficient fully sparse frameworks are rarely explored. In this work, we design a fully sparse framework, SparseAlign, with three key features: an enhanced sparse 3D backbone, a query-based temporal context learning module, and a robust detection head specially tailored for sparse features. Extensive experimental results on both OPV2V and DairV2X datasets show that our framework, despite its sparsity, outperforms the state of the art with less communication bandwidth requirements. In addition, experiments on the OPV2Vt and DairV2Xt datasets for time-aligned cooperative object detection also show a significant performance gain compared to the baseline works.
KW - cs.CV
KW - data fusion
KW - cooperative perception
KW - point cloud
KW - autonomous driving
UR - http://www.scopus.com/inward/record.url?scp=105017064770&partnerID=8YFLogxK
U2 - 10.1109/CVPR52734.2025.02077
DO - 10.1109/CVPR52734.2025.02077
M3 - Conference contribution
SN - 979-8-3315-4364-8
T3 - CVPR
SP - 22296
EP - 22305
BT - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
ER -