LAGS: Low-Altitude Gaussian Splatting with Groupwise Heterogeneous Graph Learning
For drone-based 3D reconstruction systems, GW-HGNN provides a practical solution to balance reconstruction quality and communication cost, with orders-of-magnitude speedup.
LAGS addresses inefficient resource allocation in low-altitude Gaussian splatting by proposing GW-HGNN, which models image group diversity. It achieves significant improvements in rendering metrics (PSNR, SSIM, LPIPS) and reduces computational latency by ~100x compared to MOSEK, enabling real-time deployment.
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.