Sparse-Aware Vector Quantization for Bandwidth-Efficient Collaborative 3D Semantic Occupancy Prediction
This work addresses bandwidth efficiency for collaborative perception in autonomous driving, a domain where communication constraints hinder real-world deployment.
Collaborative 3D semantic occupancy prediction suffers from a trade-off between perception gain and communication overhead. The proposed VQSOP framework uses Sparse-Aware Vector Quantization to reduce communication volume by up to 82x while achieving state-of-the-art performance.
Collaborative perception extends single-agent perception by enabling multiple vehicles to exchange complementary perceptual information. However, it introduces an inherent trade-off between perception gain and communication overhead, which is particularly severe for 3D semantic occupancy prediction that relies on fine-grained spatial structures. Existing methods typically compress 3D features into 2D, causing severe spatial information loss, or transmit dense 3D representations, hindering real-world deployment. To overcome these limitations, we propose a bandwidth-efficient collaborative Vector Quantization Semantic Occupancy Prediction (VQSOP) framework. VQSOP employs a Sparse-Aware Vector Quantization (SAVQ) mechanism that exploits 3D scene sparsity to compactly encode informative regions, drastically reducing communication overhead while preserving complete geometric context. Furthermore, to enhance structural consistency and feature continuity, we design a Dual-Branch Adaptive Spatial Refinement (ASR) module that dynamically fuses local high-frequency details with broad contextual semantics. Extensive experiments demonstrate that our approach achieves state-of-the-art performance while reducing communication volume by up to 82x.