GenAI-enabled Residual Motion Estimation for Energy-Efficient Semantic Video Communication
Shavbo Salehi, Pedro Enrique Iturria-Rivera, Medhat Elsayed, Majid Bavand, Yigit Ozcan, Melike Erol-Kantarci
TL;DR
The paper tackles the growing energy and bandwidth demands of semantic video transmission by introducing PENME, a framework that adaptively selects between CNN, optical flow, and ViT-based residual motion extraction and applies a lightweight diffusion-based latent refinement (LCM-4) at the receiver. By modeling motion with five entropy- and predictability-derived signals, PENME dynamically allocates modeling effort and signaling, reducing data size and power while preserving high semantic fidelity. Extensive experiments on Vimeo-90K show PENME achieving up to 40% latency reduction, ~90% data savings, and improvements in PSNR, MS-SSIM, and LPIPS compared with traditional and other semantic baselines. The approach emphasizes edge-deployed, per-frame adaptive processing, making semantic video transmission more practical for 5G/6G wireless networks.
Abstract
Semantic communication addresses the limitations of the Shannon paradigm by focusing on transmitting meaning rather than exact representations, thereby reducing unnecessary resource consumption. This is particularly beneficial for video, which dominates network traffic and demands high bandwidth and power, making semantic approaches ideal for conserving resources while maintaining quality. In this paper, we propose a Predictability-aware and Entropy-adaptive Neural Motion Estimation (PENME) method to address challenges related to high latency, high bitrate, and power consumption in video transmission. PENME makes per-frame decisions to select a residual motion extraction model, convolutional neural network, vision transformer, or optical flow, using a five-step policy based on motion strength, global motion consistency, peak sharpness, heterogeneity, and residual error. The residual motions are then transmitted to the receiver, where the frames are reconstructed via motion-compensated updates. Next, a selective diffusion-based refinement, the Latent Consistency Model (LCM-4), is applied on frames that trigger refinement due to low predictability or large residuals, while predictable frames skip refinement. PENME also allocates radio resource blocks with awareness of residual motion and channel state, reducing power consumption and bandwidth usage while maintaining high semantic similarity. Our simulation results on the Vimeo90K dataset demonstrate that the proposed PENME method handles various types of video, outperforming traditional communication, hybrid, and adaptive bitrate semantic communication techniques, achieving 40% lower latency, 90% less transmitted data, and 35% higher throughput. For semantic communication metrics, PENME improves PSNR by about 40%, increases MS-SSIM by roughly 19%, and reduces LPIPS by nearly 35%, compared with the baseline methods.