# CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective

Source: [CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective](<https://www.sota2.com/research/paper/68fa7a581e209131cea82a71>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:18:10.000Z

Authors: Zongheng Tang, Yi Liu, Yifan Sun, Yulu Gao, Jinyu Chen, Runsheng Xu, Si Liu

Published: 2025-08-01T06:45:12.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Object Detection on DAIR-V2X (Detection & Efficiency)](<https://www.sota2.com/research/sota/3d-object-detection-on-dair-v2x-detection-and-efficiency.md>): 3D Object Detection; DAIR-V2X; mAP@.5: 62.

- [3D Object Detection on OPV2V](<https://www.sota2.com/research/sota/3d-object-detection-on-opv2v.md>): 3D Object Detection; OPV2V; AP@0.50: 87.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.00359>)

[PDF](<https://arxiv.org/pdf/2508.00359.pdf>)