将3D高斯点云融入通信训练，提升低空图像传输与重建效率。
Efficient Transceiver Design for Aerial Image Transmission and Large-scale Scene Reconstruction
- 端到端设计融合3DGS渲染损失，联合优化通信模块。
- 采用稀疏导频方案，降低传输开销，仍保持高质量重建。
- 适合低空智能网络中的大规模三维场景重建任务。
低空智能网络（LAIN）中的大规模三维（3D）场景重建对无线图像传输的高效性要求极高。然而，现有方案难以在严重导频开销与维持重建保真度所需传输精度之间取得平衡。为此，本文提出一种基于深度学习的端到端（E2E）收发机设计，将3D高斯点云渲染（3DGS）直接嵌入训练过程。通过联合优化通信模块并引入3DGS渲染损失，该方法显著提升了场景恢复质量。此外，这一面向任务的框架支持稀疏导频方案，在低空信道条件下仍能实现鲁棒的图像恢复，大幅降低传输开销。在真实空中图像数据集上的大量实验表明，所提E2E设计显著优于现有基线，展现出更优的传输性能与精确的3D场景重建能力。
原文摘要 · Abstract (English)
Large-scale three-dimensional (3D) scene reconstruction in low-altitude intelligent networks (LAIN) demands highly efficient wireless image transmission. However, existing schemes struggle to balance severe pilot overhead with the transmission accuracy required to maintain reconstruction fidelity. To strike a balance between efficiency and reliability, this paper proposes a novel deep learning-based end-to-end (E2E) transceiver design that integrates 3D Gaussian Splatting (3DGS) directly into the training process. By jointly optimizing the communication modules via the combined 3DGS rendering loss, our approach explicitly improves scene recovery quality. Furthermore, this task-driven framework enables the use of a sparse pilot scheme, significantly reducing transmission overhead while maintaining robust image recovery under low-altitude channel conditions. Extensive experiments on real-world aerial image datasets demonstrate that the proposed E2E design significantly outperforms existing baselines, delivering superior transmission performance and accurate 3D scene reconstructions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。