Map-Assisted Remote-Sensing Image Compression at Extremely Low Bitrates

TL;DR

This paper introduces MAGC, a novel two-stage image compression framework for remote sensing images at extremely low bitrates, combining vector maps, VAE, and diffusion models to achieve high-quality, semantically accurate reconstructions.

Contribution

The paper proposes a new two-stage compression method using vector maps, VAE, and diffusion models, improving visual quality and semantic accuracy at very low bitrates.

Findings

Outperforms standard codecs in perceptual quality

Achieves higher semantic accuracy in reconstructions

Demonstrates effectiveness on remote sensing datasets

Abstract

Remote-sensing (RS) image compression at extremely low bitrates has always been a challenging task in practical scenarios like edge device storage and narrow bandwidth transmission. Generative models including VAEs and GANs have been explored to compress RS images into extremely low-bitrate streams. However, these generative models struggle to reconstruct visually plausible images due to the highly ill-posed nature of extremely low-bitrate image compression. To this end, we propose an image compression framework that utilizes a pre-trained diffusion model with powerful natural image priors to achieve high-realism reconstructions. However, diffusion models tend to hallucinate small structures and textures due to the significant information loss at limited bitrates. Thus, we introduce vector maps as semantic and structural guidance and propose a novel image compression approach named Map-Assisted Generative Compression (MAGC). MAGC employs a two-stage pipeline to compress and decompress RS images at extremely low bitrates. The first stage maps an image into a latent representation, which is then further compressed in a VAE architecture to save bitrates and serves as implicit guidance in the subsequent diffusion process. The second stage conducts a conditional diffusion model to generate a visually pleasing and semantically accurate result using implicit guidance and explicit semantic guidance. Quantitative and qualitative comparisons show that our method outperforms standard codecs and other learning-based methods in terms of perceptual quality and semantic accuracy. The dataset and code will be publicly available at https://github.com/WHUyyx/MAGC.