COSMIC: Compress Satellite Images Efficiently via Diffusion Compensation

• URL: http://arxiv.org/abs/2410.01698v2
• Date: Sat, 09 Nov 2024 13:08:42 GMT
• Title: COSMIC: Compress Satellite Images Efficiently via Diffusion Compensation
• Authors: Ziyuan Zhang, Han Qiu, Maosen Zhang, Jun Liu, Bin Chen, Tianwei Zhang, Hewu Li,
• Abstract summary: We propose COSMIC, a simple yet effective learned compression solution to transmit satellite images. We first design a lightweight encoder on satellite to achieve a high image compression ratio to save satellite-to-ground links. Then, for reconstructions on the ground, we propose a diffusion-based model to compensate image details when decoding.
• Score: 18.963383434754515
• License:
• 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 2.6~5x) 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.

Related papers

• Ultra-Low Complexity On-Orbit Compression for Remote Sensing Imagery via Block Modulated Imaging [17.334800411037836]
  This paper advances the study of compressed sensing in remote sensing image compression. By requiring only a single exposure, Block Modulated Imaging (BMI) significantly enhances imaging acquisition speeds. We propose a novel decoding network specifically designed to reconstruct images compressed under the BMI framework.
  arXiv  Detail & Related papers  (2024-12-24T13:18:00Z)
• Data downlink prioritization using image classification on-board a 6U CubeSat [0.0]
  Kyushu Institute of Technology and collaborators have launched a joint venture for a nanosatellite mission, VERTECS. The primary mission is to elucidate the formation history of stars by observing the optical-wavelength cosmic background radiation. The VERTECS satellite will be equipped with a small-aperture telescope and a high-precision attitude control system to capture the cosmic data for analysis on the ground. We propose an on-orbit system to autonomously classify and then compress desirable image data for data downlink prioritization and optimization.
  arXiv  Detail & Related papers  (2024-08-27T08:38:45Z)
• Convolutional variational autoencoders for secure lossy image compression in remote sensing [47.75904906342974]
  This study investigates image compression based on convolutional variational autoencoders (CVAE) CVAEs have been demonstrated to outperform conventional compression methods such as JPEG2000 by a substantial margin on compression benchmark datasets.
  arXiv  Detail & Related papers  (2024-04-03T15:17:29Z)
• MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model [78.4051835615796]
  This paper proposes a method called Multimodal Image Semantic Compression. It consists of an LMM encoder for extracting the semantic information of the image, a map encoder to locate the region corresponding to the semantic, an image encoder generates an extremely compressed bitstream, and a decoder reconstructs the image based on the above information. It can achieve optimal consistency and perception results while saving perceptual 50%, which has strong potential applications in the next generation of storage and communication.
  arXiv  Detail & Related papers  (2024-02-26T17:11:11Z)
• Diffusion Models for Interferometric Satellite Aperture Radar [73.01013149014865]
  Probabilistic Diffusion Models (PDMs) have recently emerged as a very promising class of generative models. Here, we leverage PDMs to generate several radar-based satellite image datasets. We show that PDMs succeed in generating images with complex and realistic structures, but that sampling time remains an issue.
  arXiv  Detail & Related papers  (2023-08-31T16:26:17Z)
• Attention-Based Generative Neural Image Compression on Solar Dynamics Observatory [12.283978726972752]
  NASA's Solar Dynamics Observatory (SDO) mission gathers 1.4 terabytes of data each day from its geosynchronous orbit in space. Recently, end-to-end optimized artificial neural networks (ANN) have shown great potential in performing image compression. We have designed an ad-hoc ANN-based image compression scheme to reduce the amount of data needed to be stored and retrieved on space missions.
  arXiv  Detail & Related papers  (2022-10-12T17:39:08Z)
• Reducing Redundancy in the Bottleneck Representation of the Autoencoders [98.78384185493624]
  Autoencoders are a type of unsupervised neural networks, which can be used to solve various tasks. We propose a scheme to explicitly penalize feature redundancies in the bottleneck representation. We tested our approach across different tasks: dimensionality reduction using three different dataset, image compression using the MNIST dataset, and image denoising using fashion MNIST.
  arXiv  Detail & Related papers  (2022-02-09T18:48:02Z)
• Small Lesion Segmentation in Brain MRIs with Subpixel Embedding [105.1223735549524]
  We present a method to segment MRI scans of the human brain into ischemic stroke lesion and normal tissues. We propose a neural network architecture in the form of a standard encoder-decoder where predictions are guided by a spatial expansion embedding network.
  arXiv  Detail & Related papers  (2021-09-18T00:21:17Z)
• UAV Localization Using Autoencoded Satellite Images [14.39926267531322]
  We propose and demonstrate a fast, robust method for using satellite images to localize an Unmanned Aerial Vehicle (UAV) In this work, we collect Google Earth (GE) images for a desired flight path offline and an autoencoder is trained to compress these images to a low-dimensional vector representation. We robustly matched UAV images from six runs spanning the lighting conditions of a single day to the same map of satellite images.
  arXiv  Detail & Related papers  (2021-02-10T19:08:10Z)
• Modeling Lost Information in Lossy Image Compression [72.69327382643549]
  Lossy image compression is one of the most commonly used operators for digital images. We propose a novel invertible framework called Invertible Lossy Compression (ILC) to largely mitigate the information loss problem.
  arXiv  Detail & Related papers  (2020-06-22T04:04:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.