Efficient Transceiver Design for Aerial Image Transmission and Large-scale Scene Reconstruction

Zeyi Ren; Jialin Dong; Wei Zuo; Yikun Wang; Bingyang Cheng; Sheng Zhou; Zhisheng Niu

cs.CVApr 13, 2026

Efficient Transceiver Design for Aerial Image Transmission and Large-scale Scene Reconstruction

Authors: Zeyi Ren, Jialin Dong, Wei Zuo, Yikun Wang, Bingyang Cheng, Sheng Zhou, Zhisheng Niu

Organizations: Department of Electronic Engineering, Tsinghua University, Beijing, China · Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong

Abstract

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.

Figures & tables

Fig. 1: Illustration of the low-altitude intelligent network imagery scenario. Traditional full pilot schemes suffer from prohibitive signaling overhead, whereas the proposed AI-driven sparse pilot transmission improves spectral efficiency for downstream 3D scene reconstruction.

Fig. 2: Architecture of the proposed task-oriented end-to-end transceiver. The transmitter utilizes a Transformer-based Moduformer for resilient constellation mapping, while the receiver employs a Deep-Rx network. Both modules are jointly optimized driven by the 3DGS rendering loss.

Fig. 3: BLER comparison of various transmission schemes versus SNR.

Fig. 4: Effective throughput comparison across varying SNRs.

Fig. 5: Quantitative evaluation of novel view synthesis quality. (a) PSNR versus training iterations. (b) SSIM versus training iterations.

Fig. 6: Qualitative visualization with and without the task-oriented loss.

Fig. 7: Qualitative visualization of the reconstructed 3D scene (HAV).

Aerial 3D Reconstruction

See all 14 papers

LAGS: Low-Altitude Gaussian Splatting with Groupwise Heterogeneous Graph Learning
Apr 18, 2026Yikun Wang, Yujie Wan, Wei Zuo +43D Gaussian Splatting Heterogeneous GNNs
The University of Hong Kong, Hong Kong, China · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China · Southern University of Science and Technology, Shenzhen, China +2
On Privacy-Preserving Image Transmission in Low-Altitude Networks: A Swin Transformer-Based Framework with Federated Learning
May 12, 2026Kexin Zhang, Lixin Li, Yuna Yan +5Semantic Communication Wireless Communications
School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710129, China · DecoreX Intelligent Technologies Co., Ltd., Xi’an 710075, China · Samsung AI Center, Cambridge CB1 2JH, UK +2
RadioFormer3D: Weakly Supervised 3D Radio Map Estimation in Low-Altitude Airspace via Generative Modeling
May 28, 2026Zheng Fang, Junjie Liu, Kangjun Liu +33D Reconstruction Wireless Communications
Pengcheng Laboratory, China · Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China · Harbin Institute of Technology, Shenzhen, China

Apr 18, 2026J/K move · Enter open · S save

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

Yikun Wang, Yujie Wan, Wei Zuo, Shuai Wang+3

The University of Hong Kong, Hong Kong, China · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China · Southern University of Science and Technology, Shenzhen, China+2

3D Gaussian Splatting Heterogeneous GNNs 3D Reconstruction Wireless Resource Allocation Aerial 3D Reconstruction

Open paper AskPDF arXiv

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

Aerial 3D Reconstruction

Explore similar work

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

On Privacy-Preserving Image Transmission in Low-Altitude Networks: A Swin Transformer-Based Framework with Federated Learning

RadioFormer3D: Weakly Supervised 3D Radio Map Estimation in Low-Altitude Airspace via Generative Modeling