Distributed Latent Representation Clustering for Efficient Multi-Satellite Image Compression.
Saved in:
| Title: | Distributed Latent Representation Clustering for Efficient Multi-Satellite Image Compression. |
|---|---|
| Authors: | Lu, Xiandong1,2 (AUTHOR), Guan, Xingyu2,3 (AUTHOR), Wang, Pengcheng2,3,4,5 (AUTHOR), Cai, Zhiming4 (AUTHOR), Zhang, Yonghe1,2,4,5 (AUTHOR) zhangyh@microsate.com |
| Source: | Remote Sensing. May2026, Vol. 18 Issue 9, p1355. 30p. |
| Subjects: | Image compression, Satellite-based remote sensing, Rate distortion theory, Data compression, Clustering algorithms |
| Abstract: | Highlights: What are the main findings? DLRC is the first framework to integrate real-time multi-satellite observation redundancy elimination into learned image compression. This method achieves a significant reduction in bits per pixel compared to baselines while maintaining virtually identical reconstruction quality. What are the implications of the main findings? DLRC establishes an efficient distributed multi-satellite image compression architecture and allows for seamless compatibility with existing models. The experimental results reveal the substantial potential of eliminating multi-satellite observation redundancy to enhance image compression performance. With the increasing number and enhanced sensing capabilities of satellites, the volume of satellite imagery has substantially surpassed the available bandwidth of satellite-to-ground links. Recently, with the adoption of commercial on-board GPUs, Learned Image Compression (LIC) offers the potential to mitigate this bottleneck by virtue of its superior rate–distortion performance over traditional codecs. However, existing LIC solutions operate in isolation on single satellites and underutilize the overlapping observations, which limits further gains in compression performance. In this paper, we propose Distributed Latent Representation Clustering (DLRC), which represents the first attempt to integrate real-time multi-satellite observation redundancy elimination into LIC. DLRC first introduces a local latent representation clustering mechanism. It discretizes the latent representation of LIC into compact cluster signatures on each satellite with lightweight computational overhead. Subsequently, DLRC presents a global cluster signature synchronization strategy. By exchanging signatures with negligible communication overhead, it enables multiple satellites to identify globally redundant local observations on a per-signature basis. By coding and downlinking only the latent representation corresponding to globally unique signatures, DLRC achieves non-redundant downlink in a training-free paradigm while remaining compatible with existing LIC architectures. Through extensive experiments, we demonstrate that DLRC achieves efficient bits per pixel reduction compared to independent LIC solutions while maintaining comparable reconstruction quality. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 193715386 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Distributed Latent Representation Clustering for Efficient Multi-Satellite Image Compression. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Lu%2C+Xiandong%22">Lu, Xiandong</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Guan%2C+Xingyu%22">Guan, Xingyu</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Pengcheng%22">Wang, Pengcheng</searchLink><relatesTo>2,3,4,5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Cai%2C+Zhiming%22">Cai, Zhiming</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Yonghe%22">Zhang, Yonghe</searchLink><relatesTo>1,2,4,5</relatesTo> (AUTHOR)<i> zhangyh@microsate.com</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. May2026, Vol. 18 Issue 9, p1355. 30p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Image+compression%22">Image compression</searchLink><br /><searchLink fieldCode="DE" term="%22Satellite-based+remote+sensing%22">Satellite-based remote sensing</searchLink><br /><searchLink fieldCode="DE" term="%22Rate+distortion+theory%22">Rate distortion theory</searchLink><br /><searchLink fieldCode="DE" term="%22Data+compression%22">Data compression</searchLink><br /><searchLink fieldCode="DE" term="%22Clustering+algorithms%22">Clustering algorithms</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Highlights: What are the main findings? DLRC is the first framework to integrate real-time multi-satellite observation redundancy elimination into learned image compression. This method achieves a significant reduction in bits per pixel compared to baselines while maintaining virtually identical reconstruction quality. What are the implications of the main findings? DLRC establishes an efficient distributed multi-satellite image compression architecture and allows for seamless compatibility with existing models. The experimental results reveal the substantial potential of eliminating multi-satellite observation redundancy to enhance image compression performance. With the increasing number and enhanced sensing capabilities of satellites, the volume of satellite imagery has substantially surpassed the available bandwidth of satellite-to-ground links. Recently, with the adoption of commercial on-board GPUs, Learned Image Compression (LIC) offers the potential to mitigate this bottleneck by virtue of its superior rate–distortion performance over traditional codecs. However, existing LIC solutions operate in isolation on single satellites and underutilize the overlapping observations, which limits further gains in compression performance. In this paper, we propose Distributed Latent Representation Clustering (DLRC), which represents the first attempt to integrate real-time multi-satellite observation redundancy elimination into LIC. DLRC first introduces a local latent representation clustering mechanism. It discretizes the latent representation of LIC into compact cluster signatures on each satellite with lightweight computational overhead. Subsequently, DLRC presents a global cluster signature synchronization strategy. By exchanging signatures with negligible communication overhead, it enables multiple satellites to identify globally redundant local observations on a per-signature basis. By coding and downlinking only the latent representation corresponding to globally unique signatures, DLRC achieves non-redundant downlink in a training-free paradigm while remaining compatible with existing LIC architectures. Through extensive experiments, we demonstrate that DLRC achieves efficient bits per pixel reduction compared to independent LIC solutions while maintaining comparable reconstruction quality. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=193715386 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/rs18091355 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 30 StartPage: 1355 Subjects: – SubjectFull: Image compression Type: general – SubjectFull: Satellite-based remote sensing Type: general – SubjectFull: Rate distortion theory Type: general – SubjectFull: Data compression Type: general – SubjectFull: Clustering algorithms Type: general Titles: – TitleFull: Distributed Latent Representation Clustering for Efficient Multi-Satellite Image Compression. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Lu, Xiandong – PersonEntity: Name: NameFull: Guan, Xingyu – PersonEntity: Name: NameFull: Wang, Pengcheng – PersonEntity: Name: NameFull: Cai, Zhiming – PersonEntity: Name: NameFull: Zhang, Yonghe IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 05 Text: May2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 20724292 Numbering: – Type: volume Value: 18 – Type: issue Value: 9 Titles: – TitleFull: Remote Sensing Type: main |
| ResultId | 1 |
