analiza aiqbench
This research introduces GW-HGNN to optimize resource allocation for low-altitude Gaussian splatting, addressing inefficiencies in drone-based 3D reconstruction caused by varying viewpoints. By transforming rendering losses into graph learning costs, the method achieves a significant reduction in computational latency while maintaining high-fidelity scene generation metrics like PSNR and SSIM. The approach represents a notable advancement in applying heterogeneous graph neural networks to real-time aerial imaging tasks within computer vision.
LAGS: Low-Altitude Gaussian Splatting with Groupwise Heterogeneous Graph Learning
arXiv:2604.16910v2 Announce Type: replace-cross 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.
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.
Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
arXiv:2604.16910 [cs.CV]
(or arXiv:2604.16910v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2604.16910 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 246 cuvinte
Subiecte conexe
When pose graphs are not enough: a failure analysis of pose-graph-based camera estimation for Gaussian splatting
arXiv · 14 oct. 2026
HDST-GNN: Heterogeneous Dynamic Spatiotemporal Graph Neural Networks for Multi-Object Tracking in UAV Aerial Imagery
arXiv · 6 iun. 2026
[AINews] not much happened today
Latent Space · 18 sept. 2026
2DGS-Planner: Rasterization-based Path Planning in 2D Gaussian Splatting Map
arXiv · 9 oct. 2026