A PPO-Based Bitrate Allocation Conditional Diffusion Model for Remote Sensing Image Compression

TL;DR

This paper introduces a novel compression framework combining a conditional diffusion model with reinforcement learning-based bitrate allocation, achieving high compression ratios while preserving important details in remote sensing images.

Contribution

It proposes a PPO-based bitrate allocation method integrated with a diffusion decoder for efficient remote sensing image compression, and releases a new high-resolution drone image dataset.

Findings

Achieves compression ratios of 19.3x on DIV2K and 21.2x on drone dataset.

Maintains task-relevant information with negligible performance loss in object detection.

Demonstrates effective balance between compression efficiency and detail preservation.

Abstract

Existing remote sensing image compression methods still explore to balance high compression efficiency with the preservation of fine details and task-relevant information. Meanwhile, high-resolution drone imagery offers valuable structural details for urban monitoring and disaster assessment, but large-area datasets can easily reach hundreds of gigabytes, creating significant challenges for storage and long-term management. In this paper, we propose a PPO-based bitrate allocation Conditional Diffusion Compression (PCDC) framework. PCDC integrates a conditional diffusion decoder with a PPO-based block-wise bitrate allocation strategy to achieve high compression ratios while maintaining strong perceptual performance. We also release a high-resolution drone image dataset with richer structural details at a consistent low altitude over residential neighborhoods in coastal urban areas. Experimental results show compression ratios of 19.3x on DIV2K and 21.2x on the drone image dataset. Moreover, downstream object detection experiments demonstrate that the reconstructed images preserve task-relevant information with negligible performance loss.