SlimComm: Doppler-Guided Sparse Queries for Bandwidth-Efficient Cooperative 3-D Perception

2025-08-18

AI Summary

To address the inter-vehicle communication bandwidth bottleneck caused by BEV feature transmission in cooperative perception, this paper proposes SlimComm. Methodologically, it introduces (1) a motion-centric dynamic map built from 4D radar Doppler information to decouple static and dynamic objects; (2) a two-stage offset-guided sparse query mechanism that generates both reference and exploratory queries to precisely localize critical regions and occlusion-prone blind spots; and (3) multi-scale gated deformable attention for low-overhead, high-fidelity cross-vehicle BEV feature fusion. SlimComm selectively transmits only BEV features from salient regions, drastically reducing communication load. Evaluated on our newly established OPV2V-R and Adver-City-R benchmarks, it achieves up to 90% bandwidth reduction while maintaining state-of-the-art detection accuracy under multi-density and severe occlusion conditions.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

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.

Problem

• Reducing bandwidth for cooperative 3D perception in CAVs
• Distinguishing moving and static objects with Doppler radar
• Optimizing feature sharing via sparse queries for accuracy

Innovation

• Doppler-guided sparse queries reduce bandwidth
• Motion-centric dynamic map distinguishes objects
• Multi-scale gated attention preserves accuracy