Skip to main navigation Skip to search Skip to main content

A Conditional Diffusion Method Based on Cross-Domain Prior Guidance for Color Enhancement of Remote Sensing Images

  • Zhengguang Song
  • , Zhijiang Li*
  • , Jiahui Song
  • *Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

Remote sensing images are susceptible to atmospheric scattering, imaging conditions, and post-processing strategies during actual acquisition, resulting in issues such as low contrast, insufficient color saturation, and overall poor visual quality. These problems significantly degrade the color quality and expressiveness of the imagery. To address these issues, a prior-guided conditional diffusion enhancement framework (PGCDE) is proposed in this paper. First, an unconditional diffusion model is built upon large-scale natural images to extract stable color priors. Then, these prior features are dynamically injected into the conditional enhancement network through an adaptive hierarchical feature fusion (AHFF) module, with a multi-domain joint loss introduced during training to constrain structural consistency. Finally, at the inference stage, a luminance-decoupled multi-scale fusion strategy is employed to recombine the generated low-frequency color tones with the high-frequency textures of the original image. Experiments on the GID-5 and LoveDA datasets demonstrate that the proposed method outperforms existing representative approaches, providing a practical solution for remote sensing image color quality enhancement that balances perceptual improvement with structure preservation.
Original languageEnglish
Article number1339
Number of pages24
JournalREMOTE SENSING
Volume18
Issue number9
Early online dateApr 2026
DOIs
StatePublished - 27 Apr 2026

Indexed by

  • EI
  • SCIE
  • Scopus

Fingerprint

Dive into the research topics of 'A Conditional Diffusion Method Based on Cross-Domain Prior Guidance for Color Enhancement of Remote Sensing Images'. Together they form a unique fingerprint.

Cite this