Deep Unfolding Real-Time Super-Resolution Using Subpixel-Shift Twin Image and Convex Self-Similarity Prior

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Chia-Hsiang, Liu, Wei-Chih, Chiu, Yu-En, Lin, Jhao-Ting
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912925992615936
author Lin, Chia-Hsiang
Liu, Wei-Chih
Chiu, Yu-En
Lin, Jhao-Ting
author_facet Lin, Chia-Hsiang
Liu, Wei-Chih
Chiu, Yu-En
Lin, Jhao-Ting
contents Multi-image super-resolution (MISR) is a critical technique for satellite remote sensing. In the perspective of information, twin-image super-resolution (TISR) is regarded as the most challenging MISR scenario, having crucial applications like the SPOT-5 supermode imaging. In TISR, an image is super-resolved by its subpixel-shift counterpart (i.e., twin image), where the two images are typically offset by half a pixel both horizontally and vertically. We formulate the less investigated TISR using a convex criterion, which is implemented using a novel deep unfolding network. In the unfolding, an embedded simple shift operator trickily addresses the coupled TISR data-fitting terms, and a transformer trained with a convex self-similarity loss function elegantly implements the proximal mapping induced by the TISR regularizer. The proposed convex self-similarity unfolding supermode super-resolution (COSUP) algorithm is interpretable and achieves state-of-the-art performance with very fast millisecond-level computational time. COSUP is also tested on real-world data, for which the subpixel shifts would not be spatially uniform, with results showing great superiority over the official CNES supermode imaging product in terms of credible metrics (e.g., natural image quality evaluator, NIQE). Source codes: https://github.com/IHCLab/COSUP.
format Preprint
id arxiv_https___arxiv_org_abs_2602_21513
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Deep Unfolding Real-Time Super-Resolution Using Subpixel-Shift Twin Image and Convex Self-Similarity Prior
Lin, Chia-Hsiang
Liu, Wei-Chih
Chiu, Yu-En
Lin, Jhao-Ting
Image and Video Processing
Multi-image super-resolution (MISR) is a critical technique for satellite remote sensing. In the perspective of information, twin-image super-resolution (TISR) is regarded as the most challenging MISR scenario, having crucial applications like the SPOT-5 supermode imaging. In TISR, an image is super-resolved by its subpixel-shift counterpart (i.e., twin image), where the two images are typically offset by half a pixel both horizontally and vertically. We formulate the less investigated TISR using a convex criterion, which is implemented using a novel deep unfolding network. In the unfolding, an embedded simple shift operator trickily addresses the coupled TISR data-fitting terms, and a transformer trained with a convex self-similarity loss function elegantly implements the proximal mapping induced by the TISR regularizer. The proposed convex self-similarity unfolding supermode super-resolution (COSUP) algorithm is interpretable and achieves state-of-the-art performance with very fast millisecond-level computational time. COSUP is also tested on real-world data, for which the subpixel shifts would not be spatially uniform, with results showing great superiority over the official CNES supermode imaging product in terms of credible metrics (e.g., natural image quality evaluator, NIQE). Source codes: https://github.com/IHCLab/COSUP.
title Deep Unfolding Real-Time Super-Resolution Using Subpixel-Shift Twin Image and Convex Self-Similarity Prior
topic Image and Video Processing
url https://arxiv.org/abs/2602.21513