LAGS: Low-Altitude Gaussian Splatting with Groupwise Heterogeneous Graph Learning

2026-04-18

AI Summary

This work addresses the inefficiency in resource allocation for 3D reconstruction from multi-UAV aerial imagery in Low-Altitude Gaussian Splatting (LAGS) by proposing a Group-wise Heterogeneous Graph Neural Network (GW-HGNN). For the first time, reconstruction loss and communication constraints are jointly modeled as a graph learning cost. By constructing non-uniform contribution relationships among image groups and introducing a two-level message-passing mechanism, GW-HGNN automatically balances data fidelity against transmission overhead. Experiments on real-world LAGS datasets demonstrate that the proposed method substantially outperforms existing approaches, achieving state-of-the-art performance across PSNR, SSIM, and LPIPS metrics while reducing inference latency to the millisecond level—yielding nearly a 100× speedup.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Low-altitude Gaussian splatting (LAGS) facilitates 3D scene reconstruction by aggregating aerial images from distributed drones. However, as LAGS prioritizes maximizing reconstruction quality over communication throughput, existing low-altitude resource allocation schemes become inefficient. This inefficiency stems from their failure to account for image diversity introduced by varying viewpoints. To fill this gap, we propose a groupwise heterogeneous graph neural network (GW-HGNN) for LAGS resource allocation. GW-HGNN explicitly models the non-uniform contribution of different image groups to the reconstruction process, thus automatically balancing data fidelity and transmission cost. The key insight of GW-HGNN is to transform LAGS losses and communication constraints into graph learning costs for dual-level message passing. Experiments on real-world LAGS datasets demonstrate that GW-HGNN significantly outperforms state-of-the-art benchmarks across key rendering metrics, including PSNR, SSIM, and LPIPS. Furthermore, GW-HGNN reduces computational latency by approximately 100x compared to the widely-used MOSEK solver, achieving millisecond-level inference suitable for real-time deployment.

Problem

• Low-altitude Gaussian Splatting
• resource allocation
• image diversity
• 3D scene reconstruction
• communication throughput

Innovation

• Gaussian Splatting
• Groupwise Heterogeneous Graph Neural Network
• Low-Altitude Aerial Imaging
• Resource Allocation
• Real-time 3D Reconstruction