Hierarchical Scale-Adaptive Diffusion Priors for Efficient Remote Sensing Dehazing.
Saved in:
| Title: | Hierarchical Scale-Adaptive Diffusion Priors for Efficient Remote Sensing Dehazing. |
|---|---|
| Authors: | Ju, Wei1 (AUTHOR), Liang, Zheng2 (AUTHOR), Chen, Huan3 (AUTHOR), Shen, Jie1,3 (AUTHOR) shenjie@czu.edu.cn |
| Source: | Remote Sensing. Jun2026, Vol. 18 Issue 12, p1907. 20p. |
| Subjects: | Haze, Image reconstruction, Probabilistic generative models, Aerial surveillance |
| Abstract: | Highlights: What are the main findings? Hierarchical Diffusion Prior Representation is developed to decompose global diffusion latents into multi-scale embeddings, enabling fine-grained and scale-aware restoration. A Scale-Adaptive Prior Injection mechanism is introduced to dynamically modulate prior contributions across feature levels, improving feature utilization and robustness. What are the implications of the main findings? The proposed method significantly improves dehazing performance under heavy and spatially variant haze, achieving superior quantitative metrics and visual quality. It provides an efficient and robust solution for remote sensing image restoration, enhancing the reliability of downstream Earth observation applications. Remote sensing image dehazing remains a formidable challenge due to complex atmospheric scattering and large-scale spatially varying degradation, which severely compromise fine-grained surface details. While recent diffusion-based restoration frameworks, such as DiffIR, have achieved remarkable efficiency by injecting compact diffusion priors into deterministic networks, they typically rely on a monolithic global Image Prior Representation (IPR). However, such a global design is suboptimal for the dehazed results of remote sensing imagery, where haze distribution exhibits strong spatial heterogeneity and scale dependency. To address this limitation, this paper presents the Hierarchical and Scale-Adaptive Diffusion Prior (HS-DiffIR) framework. Specifically, Hierarchical Image Prior Representation decomposes the holistic diffusion latent into multi-scale priors aligned with the hierarchical stages of the restoration network. Such a design facilitates fine-grained, scale-aware guidance by projecting the compact global latent into layer-specific representations, thereby bypassing the computational burden of high-dimensional generative modeling. Complementing this, the Scale-Adaptive Injection mechanism utilizes lightweight learnable coefficients to dynamically modulate the influence of diffusion priors across different feature scales, allowing the network to adaptively balance global semantic consistency and local detail recovery under dense-haze conditions. Evaluations on remote sensing benchmarks confirm that HS-DiffIR generally outperforms the DiffIR baseline. The method yields superior quantitative metrics (particularly PSNR) at a marginal computational cost while demonstrating robust detail restoration in regions subject to severe, spatially variant haze. [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: 194915040 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Hierarchical Scale-Adaptive Diffusion Priors for Efficient Remote Sensing Dehazing. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Ju%2C+Wei%22">Ju, Wei</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liang%2C+Zheng%22">Liang, Zheng</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chen%2C+Huan%22">Chen, Huan</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Shen%2C+Jie%22">Shen, Jie</searchLink><relatesTo>1,3</relatesTo> (AUTHOR)<i> shenjie@czu.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Jun2026, Vol. 18 Issue 12, p1907. 20p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Haze%22">Haze</searchLink><br /><searchLink fieldCode="DE" term="%22Image+reconstruction%22">Image reconstruction</searchLink><br /><searchLink fieldCode="DE" term="%22Probabilistic+generative+models%22">Probabilistic generative models</searchLink><br /><searchLink fieldCode="DE" term="%22Aerial+surveillance%22">Aerial surveillance</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Highlights: What are the main findings? Hierarchical Diffusion Prior Representation is developed to decompose global diffusion latents into multi-scale embeddings, enabling fine-grained and scale-aware restoration. A Scale-Adaptive Prior Injection mechanism is introduced to dynamically modulate prior contributions across feature levels, improving feature utilization and robustness. What are the implications of the main findings? The proposed method significantly improves dehazing performance under heavy and spatially variant haze, achieving superior quantitative metrics and visual quality. It provides an efficient and robust solution for remote sensing image restoration, enhancing the reliability of downstream Earth observation applications. Remote sensing image dehazing remains a formidable challenge due to complex atmospheric scattering and large-scale spatially varying degradation, which severely compromise fine-grained surface details. While recent diffusion-based restoration frameworks, such as DiffIR, have achieved remarkable efficiency by injecting compact diffusion priors into deterministic networks, they typically rely on a monolithic global Image Prior Representation (IPR). However, such a global design is suboptimal for the dehazed results of remote sensing imagery, where haze distribution exhibits strong spatial heterogeneity and scale dependency. To address this limitation, this paper presents the Hierarchical and Scale-Adaptive Diffusion Prior (HS-DiffIR) framework. Specifically, Hierarchical Image Prior Representation decomposes the holistic diffusion latent into multi-scale priors aligned with the hierarchical stages of the restoration network. Such a design facilitates fine-grained, scale-aware guidance by projecting the compact global latent into layer-specific representations, thereby bypassing the computational burden of high-dimensional generative modeling. Complementing this, the Scale-Adaptive Injection mechanism utilizes lightweight learnable coefficients to dynamically modulate the influence of diffusion priors across different feature scales, allowing the network to adaptively balance global semantic consistency and local detail recovery under dense-haze conditions. Evaluations on remote sensing benchmarks confirm that HS-DiffIR generally outperforms the DiffIR baseline. The method yields superior quantitative metrics (particularly PSNR) at a marginal computational cost while demonstrating robust detail restoration in regions subject to severe, spatially variant haze. [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=194915040 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/rs18121907 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 20 StartPage: 1907 Subjects: – SubjectFull: Haze Type: general – SubjectFull: Image reconstruction Type: general – SubjectFull: Probabilistic generative models Type: general – SubjectFull: Aerial surveillance Type: general Titles: – TitleFull: Hierarchical Scale-Adaptive Diffusion Priors for Efficient Remote Sensing Dehazing. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Ju, Wei – PersonEntity: Name: NameFull: Liang, Zheng – PersonEntity: Name: NameFull: Chen, Huan – PersonEntity: Name: NameFull: Shen, Jie IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 06 Text: Jun2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 20724292 Numbering: – Type: volume Value: 18 – Type: issue Value: 12 Titles: – TitleFull: Remote Sensing Type: main |
| ResultId | 1 |
