# COSMIC: Compress Satellite Images Efficiently via Diffusion Compensation

arXiv: https://arxiv.org/abs/2410.01698 · HTML: https://mlsanity.com/paper/2410.01698/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 56 references that are in the map.
- First posted on arXiv 2 Oct 2024.

## Builds on (most cited first, 21 of 21)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [Functional Map of the World](https://mlsanity.com/paper/1711.07846/) (2017)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [Learned Image Compression with Mixed Transformer-CNN Architectures](https://mlsanity.com/paper/2303.14978/) (2023)
- [Lossy Image Compression with Conditional Diffusion Models](https://mlsanity.com/paper/2209.06950/) (2022)
- [The Devil Is in the Details: Window-based Attention for Image Compression](https://mlsanity.com/paper/2203.08450/) (2022)
- [Density Modeling of Images using a Generalized Normalization Transformation](https://mlsanity.com/paper/1511.06281/) (2015)
- [High-Fidelity Image Compression with Score-based Generative Models](https://mlsanity.com/paper/2305.18231/) (2023)
- [Semantic Stereo for Incidental Satellite Images](https://mlsanity.com/paper/1811.08739/) (2018)
- [GhostNetV2: Enhance Cheap Operation with Long-Range Attention](https://mlsanity.com/paper/2211.12905/) (2022)
- [Computationally Efficient Neural Image Compression](https://mlsanity.com/paper/1912.08771/) (2019)
- [Tiling and Stitching Segmentation Output for Remote Sensing: Basic Challenges and Recommendations](https://mlsanity.com/paper/1805.12219/) (2018)
- [Computationally-Efficient Neural Image Compression with Shallow Decoders](https://mlsanity.com/paper/2304.06244/) (2023)
- [Efficient Nonlinear Transforms for Lossy Image Compression](https://mlsanity.com/paper/1802.00847/) (2018)
- [Content-oriented learned image compression](https://mlsanity.com/paper/2207.14168/) (2022)

## Built on by (most cited first, 3 of 3)

- [RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion](https://mlsanity.com/paper/2410.02640/) (2024)
- [GraphComp: Extreme Error-bounded Compression of Scientific Data via Temporal Graph Autoencoders](https://mlsanity.com/paper/2505.06316/) (2025)
- [Group-of-Latents: Perceptual Video Compression at Extreme Bitrates via Masked Latent Generative Modeling](https://mlsanity.com/paper/2607.19437/) (2026)

## Abstract (arXiv)

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 2.6~5x) 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.