Towards Loss-Resilient Image Coding for Unstable Satellite Networks

TL;DR

This work proposes a loss-resilient image coding approach that leverages end-to-end optimization in learned image compression (LIC), and builds on the channel-wise progressive coding framework, incorporating Spatial-Channel Rearrangement on the encoder side and Mask Conditional Aggregation on the decoder side to improve reconstruction quality with unpredictable errors.

Abstract

Geostationary Earth Orbit (GEO) satellite communication demonstrates significant advantages in emergency short burst data services. However, unstable satellite networks, particularly those with frequent packet loss, present a severe challenge to accurate image transmission. To address it, we propose a loss-resilient image coding approach that leverages end-to-end optimization in learned image compression (LIC). Our method builds on the channel-wise progressive coding framework, incorporating Spatial-Channel Rearrangement (SCR) on the encoder side and Mask Conditional Aggregation (MCA) on the decoder side to improve reconstruction quality with unpredictable errors. By integrating the Gilbert-Elliot model into the training process, we enhance the model's ability to generalize in real-world network conditions. Extensive evaluations show that our approach outperforms traditional and deep learning-based methods in terms of compression performance and stability under diverse packet loss, offering robust and efficient progressive transmission even in challenging environments. Code is available at https://github.com/NJUVISION/LossResilientLIC.

Figures (11)

• Figure 1: Visualizations of reconstruction results with packet loss. Even under progressive transmission, burst packet loss can disrupt the subsequent reconstruction, leading to unavoidable pixel error in JPEG2000 or color deviation in ProgDTD. Our proposed method demonstrates generalized resilience to unpredictable loss.
• Figure 2: Overview of the architecture of our proposed loss-resilient image coding method. AE and AD represent arithmetic encoding and decoding, respectively.
• Figure 3: A spatial-channel rearrangement example. Feature points denoted by "0" from four channels are rearranged into a grid in a new channel. When the second rearranged channel is lost, the error is distributed across all four channels.
• Figure 4: Pipeline of mask conditional aggregation module.
• Figure 5: Network simulation using Gilbert-Elliot model.