LiteSC：用于稳健无线远程手术视频传输的轻量级语义通信
LiteSC: Lightweight Semantic Communication for Robust Wireless Telesurgical Video Transmission
浏览论文内容
中文总结 AI 辅助
LiteSC提出轻量级语义通信框架，结合冻结预训练提取器与紧凑编解码，在AWGN信道下实现稳健的腹腔镜视频传输，优于H.265+LDPC的感知质量。
中文摘要 AI 辅助
可靠的腹腔镜视频对于远程手术至关重要，然而固定速率数字传输在信道条件不佳时可能急剧退化。我们提出了LiteSC，一种轻量级语义通信框架，结合了冻结的预训练提取器、紧凑的联合信源-信道编码对以及接收端自适应的手术渲染器。提取器产生的潜在表示比红-绿-蓝（RGB）输入的标量值少约97.9%，且推理时既不需要分割掩码也不需要时间参考帧。使用独立的CholecSeg8k源视频进行训练和测试，我们在加性高斯白噪声（AWGN）信道上评估了LiteSC，符号信噪比$E_s/N_0$从0到25 dB。在信道带宽比$\ ho=0.0208$（相当于每个RGB源值0.0208个复信道符号）下，峰值信噪比（PSNR）从28.7 dB上升到31.9 dB，结构相似性指数（SSIM）从0.869上升到0.919，学习感知图像块相似度（LPIPS）从0.102下降到0.048。与在相同信道符号预算下受低密度奇偶校验（LDPC）编码保护的H.265传输相比，LiteSC实现了更高的SSIM和更低的LPIPS，尽管H.265+LDPC获得了更高的峰值PSNR。这些结果表明，在所评估的AWGN条件下，腹腔镜帧重建具有优雅的退化性能。
英文摘要
Reliable laparoscopic video is essential for telesurgery, yet fixed-rate digital transmission can degrade abruptly under poor channel conditions. We propose LiteSC, a lightweight semantic communication framework combining a frozen pretrained extractor, a compact joint source--channel coding pair, and a receiver-adapted surgical renderer. The extractor produces a latent with approximately 97.9\% fewer scalar values than the red--green--blue (RGB) input, while inference requires neither segmentation masks nor temporal reference frames. Using separate CholecSeg8k source videos for training and testing, we evaluate LiteSC over an additive white Gaussian noise (AWGN) channel at symbol signal-to-noise ratios $E_s/N_0$ from 0 to 25 dB. At a channel bandwidth ratio of $ρ=0.0208$, equivalent to 0.0208 complex channel symbols per RGB source value, peak signal-to-noise ratio (PSNR) rises from 28.7 to 31.9 dB, structural similarity index measure (SSIM) from 0.869 to 0.919, and learned perceptual image patch similarity (LPIPS) falls from 0.102 to 0.048. Against H.265 transmission protected by low-density parity-check (LDPC) coding under the same channel-symbol budget, LiteSC achieves higher SSIM and lower LPIPS, although H.265+LDPC attains a higher peak PSNR. These results show graceful laparoscopic frame reconstruction under the evaluated AWGN conditions.
发表机构
- University of Warwick（华威大学）
- Institute for Applied and Translational Technologies in Surgery, University Hospitals Coventry and Warwickshire NHS Trust（考文垂和沃里克郡NHS信托大学医院应用与转化外科技术研究所）
- Nanchang University（南昌大学）
- Wuhan University of Technology（武汉理工大学）
- Zhejiang University（浙江大学）
机构由 AI 辅助整理，请以论文原文为准。
