Towards Robust Semantic Video Transmission over Block Erasure Channels

2026-07-08

AI Summary

This work addresses the degradation in video reconstruction quality caused by localized or distributed data loss over block erasure channels by proposing a semantic-aware neural joint source-channel coding (JSCC) framework. For the first time, semantic awareness is integrated into neural JSCC: spatial-domain block-wise encoding enables recovery from local erasures, while latent feature partitioning combined with a semantics-guided non-uniform erasure strategy facilitates semantic-level inpainting in the feature domain. The approach further reveals a fundamental trade-off between spatial continuity and semantic redundancy. Experimental results demonstrate that the proposed method achieves robust performance under random local losses and significantly improves reconstruction fidelity and semantic consistency in distributed low-packet-loss scenarios, thereby enhancing the semantic robustness of video transmission.

Abstract

This paper investigates semantic-aware neural joint source-channel coding (JSCC) for robust video transmission over block erasure channels. We propose a neural video compression framework exploring both spatial-domain and feature-domain designs. In the spatial domain, video frames are partitioned into blocks, enabling localized erasure handling and fine-grained robustness control via uniform erasure and two-level, semantic-guided non-uniform erasure strategies. In the feature domain, latent features are partitioned, enabling missing features to be semantically recovered while maintaining overall spatial consistency. Comprehensive experiments quantify reconstruction quality under varying uniform and non-uniform erasure probabilities. Our results show that spatial-domain JSCC excels at handling random localized losses, whereas feature-domain JSCC provides superior robustness to distributed erasures and maintains fidelity under low-loss scenarios. The analysis highlights the trade-offs between spatial continuity and semantic redundancy, offering insights for designing robust, task-aware video communication systems.

Problem

• semantic video transmission
• block erasure channels
• robustness
• neural joint source-channel coding
• video communication

Innovation

• semantic-aware JSCC
• block erasure channels
• neural video compression
• feature-domain recovery
• non-uniform erasure