发表机构
Shanghai Jiao Tong University; Huawei Technologies Ltd.; Central Media Technology Institute（上海交通大学; 华为技术有限公司; 中央媒体技术研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对学习型图像压缩的抗丢包问题，提出ICR、ICG机制及双层双分支自回归结构，实验显示其在丢包场景下的重建质量和稳定性均优于现有方法，且可泛化到突发丢包场景。
AI 中文摘要
学习型图像压缩（LIC）已取得令人瞩目的率失真性能，但现有方法对数据包丢失仍高度敏感，而数据包丢失是卫星通信和应急通信中的常见挑战。这种脆弱性源于分组阶段的非均匀信息分布，以及熵编码阶段的顺序解码依赖关系。本文提出一种端到端抗丢包图像压缩方案，同时解决这两个问题：在分组前，引入信道间重分配（ICR）机制以重新分配信道能量，防止关键信息集中在小部分信道中；随后，采用交错信道分组（ICG）策略以步长方式划分潜在信道，将信息分散到各个数据包中，且每个数据包保持在受限大小内；为限制丢包导致的级联误差，采用双层双分支自回归结构以缩短依赖链。大量实验表明，本文方法在重建质量和稳定性上均优于现有方法：在丢包率为20%时，相比LossResilientLIC，其平均峰值信噪比（PSNR）提升1.84 dB，同时PSNR方差降低一个数量级；值得注意的是，仅在均匀随机丢包下训练的模型，可泛化到由Gilbert-Elliott信道建模的突发丢包场景，且优于专门针对此类条件训练的方法。
英文摘要
Learned image compression (LIC) has achieved impressive rate-distortion performance. However, existing methods remain highly vulnerable to packet loss, a common challenge in satellite and emergency communications. This vulnerability stems from non-uniform information distribution at the packetization stage and sequential decoding dependencies at the entropy coding stage. We propose an end-to-end loss-resilient image compression scheme that addresses both. Before packetization, we introduce an Inter-Channel Redistribution (ICR) mechanism to redistribute channel energy, preventing critical information concentrating in a small subset of channels. Then, an Interleaved Channel Grouping (ICG) strategy partitions latent channels in a strided manner to disperse information across packets, with each packet kept within constrained sizes. To limit cascading errors from lost packets, we adopt a two-layer dual-branch autoregressive structure to shorten the dependency chain. Extensive experiments demonstrate that our method consistently outperforms existing approaches in both reconstruction quality and stability. At 20% packet loss, it achieves an average PSNR gain of 1.84 dB over LossResilientLIC while reducing PSNR variance by an order of magnitude. Notably, trained under uniform random loss only, our model generalizes to bursty loss modeled by the Gilbert-Elliott channel, outperforming methods explicitly trained for such conditions.
Comments16 pages, 12 figures, 8 tables. Joint first authors: Yuhang Wei and Chuqin Zhou. Corresponding author: Guo Lu. To appear in Proceedings of the 34th ACM International Conference on Multimedia (MM '26), November 10-14, 2026, Rio de Janeiro, Brazil
