CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911086948646912 |
|---|---|
| author | Tang, Zongheng Liu, Yi Sun, Yifan Gao, Yulu Chen, Jinyu Xu, Runsheng Liu, Si |
| author_facet | Tang, Zongheng Liu, Yi Sun, Yifan Gao, Yulu Chen, Jinyu Xu, Runsheng Liu, Si |
| contents | Collaborative perception shares information among different agents and helps solving problems that individual agents may face, e.g., occlusions and small sensing range. Prior methods usually separate the multi-agent fusion and multi-time fusion into two consecutive steps. In contrast, this paper proposes an efficient collaborative perception that aggregates the observations from different agents (space) and different times into a unified spatio-temporal space simultanesouly. The unified spatio-temporal space brings two benefits, i.e., efficient feature transmission and superior feature fusion. 1) Efficient feature transmission: each static object yields a single observation in the spatial temporal space, and thus only requires transmission only once (whereas prior methods re-transmit all the object features multiple times). 2) superior feature fusion: merging the multi-agent and multi-time fusion into a unified spatial-temporal aggregation enables a more holistic perspective, thereby enhancing perception performance in challenging scenarios. Consequently, our Collaborative perception with Spatio-temporal Transformer (CoST) gains improvement in both efficiency and accuracy. Notably, CoST is not tied to any specific method and is compatible with a majority of previous methods, enhancing their accuracy while reducing the transmission bandwidth. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00359 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective Tang, Zongheng Liu, Yi Sun, Yifan Gao, Yulu Chen, Jinyu Xu, Runsheng Liu, Si Computer Vision and Pattern Recognition Collaborative perception shares information among different agents and helps solving problems that individual agents may face, e.g., occlusions and small sensing range. Prior methods usually separate the multi-agent fusion and multi-time fusion into two consecutive steps. In contrast, this paper proposes an efficient collaborative perception that aggregates the observations from different agents (space) and different times into a unified spatio-temporal space simultanesouly. The unified spatio-temporal space brings two benefits, i.e., efficient feature transmission and superior feature fusion. 1) Efficient feature transmission: each static object yields a single observation in the spatial temporal space, and thus only requires transmission only once (whereas prior methods re-transmit all the object features multiple times). 2) superior feature fusion: merging the multi-agent and multi-time fusion into a unified spatial-temporal aggregation enables a more holistic perspective, thereby enhancing perception performance in challenging scenarios. Consequently, our Collaborative perception with Spatio-temporal Transformer (CoST) gains improvement in both efficiency and accuracy. Notably, CoST is not tied to any specific method and is compatible with a majority of previous methods, enhancing their accuracy while reducing the transmission bandwidth. |
| title | CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.00359 |