Hybrid Deep Learning Models for Remote Sensing Image Processing

doi:10.1109/jproc.2025.3638871

Hybrid Deep Learning Models for Remote Sensing Image Processing

2025-12-12

0

PRE

AI

Jón Atli Benediktsson

DOI：10.1109/jproc.2025.3638871

Original

Original request for help

Save

Abstract

En 中文

Core image processing tasks, such as super-resolution, denoising, deblurring, pansharpening, and atmospheric correction, underpin all optical remote sensing (RS) pipelines. Errors at this stage propagate through downstream applications, distorting land-cover maps, change detection, and climate records. Classical physics-based models capture sensor optics, radiometry, and geometry but struggle with complex noise and scene variability. In contrast, deep learning (DL) methods offer powerful data-driven solutions yet often act as closed boxes, ignoring physical constraints and overfitting to spurious patterns. Hybrid DL (HDL) approaches bridge this gap by integrating physical models with neural architectures, combining interpretability and data adaptivity. This article surveys the emerging landscape of HDL methods in RS image processing, outlining their theoretical foundations, motivations, and design philosophies. We categorize fusion strategies, from model-embedded schemes (e.g., plug-and-play (PnP) and unrolling) to model-guided learning (e.g., deep image prior (DIP) and unsupervised frameworks), and discuss how they enhance trust, robustness, and physical consistency in RS image analysis.

Keywords:

Deep image prior (DIP)

deep learning (DL)

hybrid method

image processing

physical model

plug-and-play (PnP)

remote sensing (RS)

unrolling

Hybrid Deep Learning Models for Remote Sensing Image Processing

Abstract

Journal

Organization