SlimComm: Doppler-Guided Sparse Queries for Bandwidth-Efficient Cooperative 3-D Perception
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_ | 1866908493152256000 |
|---|---|
| author | Yazgan, Melih Wu, Qiyuan Hamdard, Iramm Li, Shiqi Zoellner, J. Marius |
| author_facet | Yazgan, Melih Wu, Qiyuan Hamdard, Iramm Li, Shiqi Zoellner, J. Marius |
| contents | Collaborative perception allows connected autonomous vehicles (CAVs) to overcome occlusion and limited sensor range by sharing intermediate features. Yet transmitting dense Bird's-Eye-View (BEV) feature maps can overwhelm the bandwidth available for inter-vehicle communication. We present SlimComm, a communication-efficient framework that integrates 4D radar Doppler with a query-driven sparse scheme. SlimComm builds a motion-centric dynamic map to distinguish moving from static objects and generates two query types: (i) reference queries on dynamic and high-confidence regions, and (ii) exploratory queries probing occluded areas via a two-stage offset. Only query-specific BEV features are exchanged and fused through multi-scale gated deformable attention, reducing payload while preserving accuracy. For evaluation, we release OPV2V-R and Adver-City-R, CARLA-based datasets with per-point Doppler radar. SlimComm achieves up to 90% lower bandwidth than full-map sharing while matching or surpassing prior baselines across varied traffic densities and occlusions. Dataset and code will be available at: https://url.fzi.de/SlimComm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_13007 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SlimComm: Doppler-Guided Sparse Queries for Bandwidth-Efficient Cooperative 3-D Perception Yazgan, Melih Wu, Qiyuan Hamdard, Iramm Li, Shiqi Zoellner, J. Marius Computer Vision and Pattern Recognition Collaborative perception allows connected autonomous vehicles (CAVs) to overcome occlusion and limited sensor range by sharing intermediate features. Yet transmitting dense Bird's-Eye-View (BEV) feature maps can overwhelm the bandwidth available for inter-vehicle communication. We present SlimComm, a communication-efficient framework that integrates 4D radar Doppler with a query-driven sparse scheme. SlimComm builds a motion-centric dynamic map to distinguish moving from static objects and generates two query types: (i) reference queries on dynamic and high-confidence regions, and (ii) exploratory queries probing occluded areas via a two-stage offset. Only query-specific BEV features are exchanged and fused through multi-scale gated deformable attention, reducing payload while preserving accuracy. For evaluation, we release OPV2V-R and Adver-City-R, CARLA-based datasets with per-point Doppler radar. SlimComm achieves up to 90% lower bandwidth than full-map sharing while matching or surpassing prior baselines across varied traffic densities and occlusions. Dataset and code will be available at: https://url.fzi.de/SlimComm. |
| title | SlimComm: Doppler-Guided Sparse Queries for Bandwidth-Efficient Cooperative 3-D Perception |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.13007 |