GeoFovea-GS: Geometry-Aware Cross-Layer Gaussian Splatting for Wireless Aerial VR

2026-07-14

AI Summary

This work addresses the challenges of wireless over-the-air virtual reality, which is constrained by limited bandwidth, latency, and power consumption. Existing 3D Gaussian Splatting (3DGS) methods suffer from significant visual degradation due to geometric inaccuracies, while conventional resource allocation schemes fail to model geometry-sensitive distortions effectively. To overcome these limitations, the paper proposes a geometry-aware cross-layer optimization framework that integrates foveated rendering, geometric consistency, and perceptual importance to jointly optimize pose-driven 3DGS rendering and tile-level transmission strategies. A novel foveated geometry-aware distortion metric is introduced, uniquely combining geometric criticality with perceptual significance to guide communication resource scheduling—surpassing the constraints of pixel-level or channel-aware approaches. Experimental results on real-world 3DGS scenes demonstrate that the proposed method substantially reduces transmission overhead while enhancing immersive rendering quality.

Abstract

Wireless aerial virtual reality (VR) aims to provide immersive access to large-scale scenes, but high-resolution view generation and delivery are jointly constrained by limited bandwidth, latency, and power. 3D Gaussian Splatting (3DGS) can reduce the payload by rendering views from compact pose information, yet its geometry errors may cause severe VR quality degradation. Existing channel-aware or pixel-level resource allocation schemes fail to capture such geometry-sensitive distortion. To address this issue, this paper proposes GeoFovea-GS as a geometry-aware cross-layer framework for communication-efficient wireless aerial VR. A foveated geometry-aware distortion metric is developed to characterize photometric rendering error, geometric inconsistency, and view-dependent perceptual importance in a unified form. Based on this metric, the joint selection of pose-only 3DGS rendering and image/tile correction transmission is formulated as a cross-layer optimization problem under wireless constraints. A lightweight value-of-information scheduler is further developed to allocate communication resources to regions that are both geometry-critical and perceptually important. Experiments on real-world 3DGS scenes demonstrate that GeoFovea-GS achieves superior immersive rendering quality with substantially reduced transmission cost.

Problem

• Wireless aerial VR
• 3D Gaussian Splatting
• geometry-aware distortion
• cross-layer optimization
• foveated rendering

Innovation

• Geometry-Aware Distortion
• Cross-Layer Optimization
• 3D Gaussian Splatting
• Foveated Rendering
• Wireless VR