Generative Video Semantic Communication via Multimodal Semantic Fusion with Large Model
This work addresses the problem of immersive video transmission for 6G networks, representing an incremental advancement by applying existing generative AI methods to semantic communication.
The paper tackles the challenge of high-quality video reconstruction under low bandwidth and noisy conditions in 6G communications by proposing a generative video semantic communication framework that fuses multimodal semantics using large models, achieving a CLIP score exceeding 0.92 at an ultra-low channel bandwidth ratio of 0.0057 for SNR > 0 dB.
Despite significant advancements in traditional syntactic communications based on Shannon's theory, these methods struggle to meet the requirements of 6G immersive communications, especially under challenging transmission conditions. With the development of generative artificial intelligence (GenAI), progress has been made in reconstructing videos using high-level semantic information. In this paper, we propose a scalable generative video semantic communication framework that extracts and transmits semantic information to achieve high-quality video reconstruction. Specifically, at the transmitter, description and other condition signals (e.g., first frame, sketches, etc.) are extracted from the source video, functioning as text and structural semantics, respectively. At the receiver, the diffusion-based GenAI large models are utilized to fuse the semantics of the multiple modalities for reconstructing the video. Simulation results demonstrate that, at an ultra-low channel bandwidth ratio (CBR), our scheme effectively captures semantic information to reconstruct videos aligned with human perception under different signal-to-noise ratios. Notably, the proposed ``First Frame+Desc." scheme consistently achieves CLIP score exceeding 0.92 at CBR = 0.0057 for SNR > 0 dB. This demonstrates its robust performance even under low SNR conditions.