Search papers, labs, and topics across Lattice.
This paper introduces a Sparse-Aware Vector Quantization Semantic Occupancy Prediction (VQSOP) framework that enhances collaborative 3D semantic occupancy prediction by efficiently encoding spatial information. By leveraging a Sparse-Aware Vector Quantization mechanism, the method significantly reduces communication overhead while maintaining the integrity of geometric context. Experimental results show that VQSOP achieves state-of-the-art performance with up to 82x reduction in communication volume, addressing the critical trade-off between perception gain and bandwidth efficiency in collaborative perception systems.
Achieving up to 82x reduction in communication volume without sacrificing spatial accuracy could revolutionize collaborative perception in autonomous vehicles.
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.
