Multipath Adaptive Video Streaming with Multiple Description Neural Video Codec over 5G Networks
2026-08-24 • Networking and Internet Architecture
Networking and Internet Architecture
AI summaryⓘ
The authors identify that current video streaming methods struggle with 5G networks because video parts depend on each other, causing stalls if some data is delayed or lost during changing network conditions. They propose NeuralMDC, a new video codec that breaks video chunks into independent pieces that can be decoded separately, so missing some pieces only reduces quality instead of causing playback to stop. Their system also smartly distributes these pieces across multiple 5G paths. Tests show their method improves video quality and user experience while reducing stalls compared to existing approaches.
5G networksvideo codecmultipath streamingmultiple description codingvideo qualitynetwork handoversvideo bufferingquality of experienceneural codecsvideo chunk
Authors
Xinyue Hu, Ziyan Wu, Jiaxiang Tang, Wei Ye, Qixin Zhang, Eman Ramadan, Ali Anwar, Zhi-Li Zhang
Abstract
5G networks employ multiple radio channels to meet growing demands for bandwidth and high-resolution video streaming for emerging applications. However, existing multipath video systems are largely designed around monolithic codecs, which require sufficiently complete chunk delivery, or layered codecs, which depend on timely base-layer delivery. Under fast-varying 5G conditions with blockage, handovers, and heterogeneous path capacities, we observe that decoding dependencies in existing codecs make multipath delivery fragile: transient under-delivery of critical video data can directly trigger stalls and degrade QoE. This paper proposes NeuralMDC, a neural multiple-description video codec co-designed with multipath streaming for dynamic 5G networks. NeuralMDC encodes each video chunk into independently decodable and mutually refinable description streams, each spanning the full chunk. This design changes the multipath delivery unit from dependent packets or layers to independent chunk-level streams, so missing streams primarily reduce quality rather than making the chunk undecodable. Built on NeuralMDC, we develop a user-space multipath streaming system that maps description streams to heterogeneous 5G paths with simple yet effective scheduling logic. Across trace-driven emulation and operational 5G experiments, NeuralMDC improves QoE by 26%-44% over existing monolithic, layered, and neural streaming systems, improves video quality by up to 41.8%, and keeps stall ratios below 0.32%.