Tube-Structured Incremental Semantic HARQ for Generative Video Receivers

TL;DR

This paper introduces a tube-structured receiver-driven semantic HARQ method for generative video reconstruction, improving recovery speed and robustness under constrained budgets compared to block-based approaches.

Contribution

It proposes a novel tube-structured retransmission primitive that enhances recovery efficiency and stability in semantic video communication systems.

Findings

Tube-structured requests outperform block-based methods in recovery speed.

The method achieves lower recovery costs in moderate-to-harsh channel conditions.

Final video quality remains comparable to existing approaches.

Abstract

Generative semantic communication uses receiver-side generative priors to reconstruct visual content from compact semantics, making it attractive for bandwidth-limited multimedia delivery. For video, reliable recovery remains difficult because errors accumulate over time, useful evidence is temporally correlated, and the receiver must make decisions under limited interaction, retransmission, and reconstruction budgets. Existing generative semantic communication studies mainly emphasize representation, compression, or generative reconstruction, while recent error-resilient and semantic-HARQ methods still largely operate on encoder-defined or frame-block retransmission units. This paper studies receiver-driven semantic HARQ for generative video reconstruction under a budget-constrained AoIS-AUC objective and argues that the retransmission primitive is itself an important system design variable. We propose tube-structured package-native requests, in which temporally local packages are the channel-visible HARQ objects and are transmitted, dropped, received, and committed at package granularity. Under a controlled comparison protocol with matched backbone, budgets, and channel model, this primitive yields lower time-weighted recovery cost than competitive block-based baselines in practically relevant moderate-to-harsh regimes, while the gap naturally shrinks in near-clean channels. The gain mainly appears as earlier stabilization of the recovery trajectory, while final-quality endpoints remain broadly comparable, and it persists even against a tube-aware block-ranking baseline.