Lune

NeurIPS2024Top-tier venue

COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation

Ziyuan Zhang, Han Qiu, Maosen Zhang, Jun Liu, Bin Chen, Tianwei Zhang, Hewu Li

Abstract

With the rapidly increasing number of satellites in space and their enhanced capabilities, the amount of earth observation images collected by satellites is exceeding the transmission limits of satellite-to-ground links. Although existing learned image compression solutions achieve remarkable performance by using a sophisticated encoder to extract fruitful features as compression and using a decoder to reconstruct, it is still hard to directly deploy those complex encoders on current satellites' embedded GPUs with limited computing capability and power supply to compress images in orbit. In this paper, we propose COSMIC, a simple yet effective learned compression solution to transmit satellite images. We first design a lightweight encoder (i.e. reducing FLOPs by 2.6 ∼ 5×) on satellite to achieve a high image compression ratio to save satellite-to-ground links. Then, for reconstructions on the ground, to deal with the feature extraction ability degradation due to simplifying encoders, we propose a diffusion-based model to compensate image details when decoding. Our insight is that satellite's earth observation photos are not just images but indeed multi-modal data with a nature of Text-to-Image pairing since they are collected with rich sensor data (e.g. coordinates, timestamp, etc.) that can be used as the condition for diffusion generation. Extensive experiments show that COSMIC outperforms state-of-the-art baselines on both perceptual and distortion metrics. The code is publicly available at https://github.com/Joanna-0421/COSMIC .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Implicit Models
  • Denoising Diffusion Restoration Models cites Denoising Diffusion Implicit Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on15

  1. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  2. Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
  3. Denoising Diffusion Restoration ModelsBahjat Kawar, Michael Elad, Stefano Ermon, Jiaming SongNeurIPS 2022 · 1,439 citations
  4. High-Fidelity Generative Image CompressionFabian Mentzer, George Toderici, Michael Tschannen, Eirikur AgustssonNeurIPS 2020 · 675 citations
  5. GhostNetV2: Enhance Cheap Operation with Long-Range AttentionYehui Tang, Kai Han, Jianyuan Guo, Chang Xu et al.NeurIPS 2022 · 634 citations

Related papers

  1. DeepSpace: Super Resolution Powered Efficient and Reliable Satellite Image Data AcquistionChuanhao Sun, Yu Zhang, Bill Tao, Deepak Vasisht et al.SIGCOMM 2025 · 3 citations
  2. Cosmos: Compressed and Smooth Latent Space for Text Diffusion ModelingViacheslav Meshchaninov, Egor Chimbulatov, Alexander Shabalin, Aleksandr Abramov et al.NeurIPS 2025
  3. OSCAR: One-Step Diffusion Codec Across Multiple Bit-ratesJinpei Guo, Yifei Ji, Zheng Chen, Kai Liu et al.NeurIPS 2025 · 25 citations
  4. AstroCompress: A benchmark dataset for multi-purpose compression of astronomical dataTuan Truong, Rithwik Sudharsan, Yibo Yang, Peter Xiangyuan Ma et al.ICLR 2025
  5. Joint Global and Local Hierarchical Priors for Learned Image CompressionJun-Hyuk Kim, Byeongho Heo, Jong-Seok LeeCVPR 2022 · 98 citations
Dusk over the sea between two cliffs drawn in fine vertical lines