Vision-Aided ISAC in Low-Altitude Economy Networks via De-Diffused Visual Priors

TL;DR

This paper introduces a vision-aided ISAC framework for UAV-based low-altitude networks, combining visual priors and radar data to optimize resource control while preserving privacy.

Contribution

It proposes a novel De-Diffusion model for extracting semantic tokens and a two-stage control algorithm for joint resource optimization in low-altitude networks.

Findings

Achieves within 4% of raw-image upper bound performance.

Outperforms baselines in reward, robustness, and semantic fidelity.

Preserves user privacy and scalability in dense environments.

Abstract

Emerging low-altitude economy networks (LAENets) require agile and privacy-preserving resource control under dynamic agent mobility and limited infrastructure support. To meet these challenges, we propose a vision-aided integrated sensing and communication (ISAC) framework for UAV-assisted access systems, where onboard masked De-Diffusion models extract compact semantic tokens, including agent type, activity class, and heading orientation, while explicitly suppressing sensitive visual content. These tokens are fused with mmWave radar measurements to construct a semantic risk heatmap reflecting motion density, occlusion, and scene complexity, which guides access technology selection and resource scheduling. We formulate a multi-objective optimization problem to jointly maximize weighted energy and perception efficiency via radio access technology (RAT) assignment, power control, and beamforming, subject to agent-specific QoS constraints. To solve this, we develop De-Diffusion-driven vision-aided risk-aware resource optimization algorithm DeDiff-VARARO, a novel two-stage cross-modal control algorithm: the first stage reconstructs visual scenes from tokens via De-Diffusion model for semantic parsing, while the second stage employs a deep deterministic policy gradient (DDPG)-based policy to adapt RAT selection, power control, and beam assignment based on fused radar-visual states. Simulation results show that DeDiff-VARARO consistently outperforms baselines in reward convergence, link robustness, and semantic fidelity, achieving within $4\%$ of the performance of a raw-image upper bound while preserving user privacy and scalability in dense environments.