A variational autoencoder inspired unsupervised remote sensing image super resolution method with multi-degradation

In current super-resolution (SR) research, blind SR models capable of handling multiple degradations have attracted significant attention. Inspired by variational autoencoders (VAEs) that model data distributions through latent representations, this paper proposes a VAE framework for unsupervised re...

Full description

Saved in:
Bibliographic Details
Published in:International journal of applied earth observation and geoinformation Vol. 144; p. 104885
Main Authors: Zhang, Ning, Wang, Yongcheng, Li, Gang, Xu, Dongdong, Werner, Martin
Format: Journal Article
Language:English
Published: Elsevier B.V 01.11.2025
Elsevier
Subjects:
Multi-degradation
Remote sensing image (RSI)
Super-resolution (SR)
Unsupervised learning
Variational autoencoder (VAE)
Variational autoencoder (VAE)
Multi-degradation
Super-resolution (SR)
Unsupervised learning
Remote sensing image (RSI)
ISSN:1569-8432
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In current super-resolution (SR) research, blind SR models capable of handling multiple degradations have attracted significant attention. Inspired by variational autoencoders (VAEs) that model data distributions through latent representations, this paper proposes a VAE framework for unsupervised remote sensing image (RSI) SR. VAEs excel at learning rich latent representations, modeling probabilistic distributions of input data and unsupervised learning, making them inherently well-suited to real-world blind SR scenarios. The proposed framework consists of an encoder that maps low-resolution (LR) images into a latent space and a decoder that reconstructs super-resolved images from the latent representations. To enhance latent modeling, an alternating optimization strategy is implemented for training the encoder and decoder. Furthermore, a comprehensive loss function and a latent coding regularization strategy are designed to constrain latent representations while maintaining image domain consistency. Experimental results demonstrate that on synthetic data, our method achieves favorable performance in both visual quality and quantitative metrics. It also demonstrates competitively performance compared to supervised methods, particularly in 4× and 8× SR tasks. Additionally, evaluations on Jilin-1 satellite RSIs further validate the effectiveness of our approach. •The unsupervised SR method handles multi-degradation with satisfying performance.•The encoder and decoder are trained alternately.•The decoder decodes latent code into SR image with fine details.•Constraining latent code with comprehensive loss improves the SR results.•Regularization strategy improves SR performance on large ratios 4 and 8.
ISSN:1569-8432
DOI:10.1016/j.jag.2025.104885