Generative Transmission: Rethinking Computation, Bandwidth, and Memory in Communication
2026-07-20 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present GenTrans, a new way to send videos when internet connections are very slow or unstable. Instead of focusing on sending exact video pixels, their method uses smart generative models to help reconstruct videos on the receiver's side, making the video look good even with little data. They also optimize the use of memory and computing power to keep the process efficient and reliable. Tests show their approach manages to send videos better and faster in tough network conditions while maintaining good visual quality.
AI FlowGenerative Video CompressionUltra-low-bitrateWeak-network conditionsGenerative modelsVideo communicationBandwidth optimizationPerceptual qualityCross-clip memory reuse
Authors
Xiangyu Chen, Jixiang Luo, Yuankai Fan, Haibin Huang, Chi Zhang, Xuelong Li
Abstract
Under the AI Flow framework, communication is shifting from transmitting fidelity-oriented information flows toward delivering task-oriented and perception-oriented token flows across heterogeneous network resources. Video communication is a fundamental component of modern information networks. However, under ultra-low-bandwidth and weak-network conditions, conventional video coding and transmission methods, which are primarily optimized for pixel-level fidelity, often struggle to balance visual usability, transmission efficiency, and robustness to unstable links. With the rapid advancement of generativemodels, video communication is also moving from precise signal reconstruction toward receiver-side perceptual utility and system-level usability. In this paper, we propose Generative Transmission (GenTrans) for video communication under ultra-low-bandwidth and weak-network conditions. Built upon Generative Video Compression (GVC), GenTrans formulates video transmission as a joint optimization problem involving bandwidth, computation, and memory, rather than treating it merely as a signal coding task. By leveraging generative priors, cross-clip memory reuse, runtime state reuse, and weak-network-aware transport, GenTrans significantly reduces transmission overhead while enabling visually coherent and practically useful reconstruction. Experimental results show that GenTrans supports effective video transmission under ultra-low-bitrate and weak-network conditions, achieving improved transmission efficiency, decoding efficiency, and robustness while preserving perceptual quality.