用语义令牌压缩，让车载系统在低带宽下也能高效协同感知。
DinoLink: A Token-Centric Representation Compression Framework for Bandwidth-Constrained Collaborative V2X Perception
- 以语义令牌为中心，通过筛选关键目标和向量化压缩特征
- 相比原始传输降低139倍码率，nuScenes上仍保持32.8% mAP
- 适合低带宽车联网场景，如LoRa，加速达34.5倍
高精度远程感知常受车辆-万物（V2X）网络严重带宽限制。本文提出DinoLink，一种以令牌为中心的压缩框架，将原始像素传输替换为离散语义通信，实现车云协同推理。DinoLink采用双稀疏架构：显著性感知选择器剔除冗余背景令牌，残差向量量化（RVQ）模块将特征压缩为紧凑的码本索引。仅传输轻量级索引与位置先验，相较未压缩传输实现139倍码率降低，同时在nuScenes数据集上保持32.8% mAP的竞争力。部署仿真进一步表明，在窄带环境（如LoRa）中可实现34.5倍加速。结果证实DinoLink是受限V2X场景下高保真远程感知的鲁棒、高效前端。代码已公开于https://github.com/UGA-MOBILITY-LAB/dino_link。
原文摘要 · Abstract (English)
High-precision remote perception is often hindered by the severe bandwidth constraints of Vehicle-to-Everything (V2X) networks. We propose \textit{DinoLink}, a token-centric compression framework that replaces raw pixel streaming with discrete semantic communication for vehicle-cloud collaborative inference. DinoLink employs a dual-sparsity architecture: a saliency-aware selector prunes redundant background tokens, while a Residual Vector Quantization (RVQ) module collapses features into compact codebook indices. By transmitting only lightweight indices and positional priors, DinoLink achieves a $139\times$ bitrate reduction compared to uncompressed transmission while maintaining a competitive 32.8\% mAP on the nuScenes dataset. Deployment simulations further demonstrate a $34.5\times$ acceleration in narrow-band environments, such as LoRa. Our results substantiate DinoLink as a robust, bandwidth-efficient frontend for high-fidelity remote perception in constrained V2X scenarios. The code is publicly available at https://github.com/UGA-MOBILITY-LAB/dino_link.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。