NesTD-Net: Deep NESTA-Inspired Unfolding Network With Dual-Path Deblocking Structure for Image Compressive Sensing
IEEE Transactions on Image Processing · 2024 · 33 · 1923-1937
DOI: 10.1109/tip.2024.3371351 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Hongping Gan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 49-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic Research Programs of Taicang, Innovation Workstation of State Key Laboratory of Intelligent Gaming.
Abstract (Originalsprache)
Deep compressive sensing (CS) has become a prevalent technique for image acquisition and reconstruction. However, existing deep learning (DL)-based CS methods often encounter challenges such as block artifacts and information loss during iterative reconstruction, particularly at low sampling rates, resulting in a reduction of reconstructed details. To address these issues, we propose NesTD-Net, an unfolding-based architecture inspired by the NESTA algorithm, designed for image CS. NesTD-Net integrates DL modules into NESTA iterations, forming a deep network that continuously iterates to minimize the l1 -norm CS problem, ensuring high-quality image CS. Utilizing a learned sampling matrix for measurements and an initialization module for initial estimate, NesTD-Net then introduces Iteration Sub-Modules derived from the NESTA algorithm (i.e., Yk , Zk , and Xk ) during reconstruction stages to iteratively solve the l1 -norm CS reconstruction. Additionally, NesTD-Net incorporates a Dual-Path Deblocking Structure (DPDS) to facilitate feature information flow and mitigate block artifacts, enhancing image detail reconstruction. Furthermore, DPDS exhibits remarkable versatility and demonstrates seamless integration with other unfolding-based methods, offering the potential to enhance their performance in image reconstruction. Experimental results demonstrate that our proposed NesTD-Net achieves better performance compared to other state-of-the-art methods in terms of image quality metrics such as SSIM and PSNR, as well as visual perception on several public benchmark datasets.
Förderung
- National Natural Science Foundation of China
- Basic Research Programs of Taicang
- Innovation Workstation of State Key Laboratory of Intelligent Gaming
Zitieren
APA
Gan, H., Guo, Z., & Liu, F. (2024). NesTD-Net: Deep NESTA-Inspired Unfolding Network With Dual-Path Deblocking Structure for Image Compressive Sensing. IEEE Transactions on Image Processing, 33, 1923-1937. https://doi.org/10.1109/tip.2024.3371351
Vancouver
Gan H, Guo Z, Liu F. NesTD-Net: Deep NESTA-Inspired Unfolding Network With Dual-Path Deblocking Structure for Image Compressive Sensing. IEEE Transactions on Image Processing. 2024;33:1923-1937. doi:10.1109/tip.2024.3371351
BibTeX
@article{Gan2024,
author = {Gan, Hongping and Guo, Zhen and Liu, Feng},
title = {NesTD-Net: Deep NESTA-Inspired Unfolding Network With Dual-Path Deblocking Structure for Image Compressive Sensing},
journal = {IEEE Transactions on Image Processing},
year = {2024},
volume = {33},
pages = {1923--1937},
doi = {10.1109/tip.2024.3371351}
}
EUVIMED