Fully 1 × 1 Convolutional Network for Lightweight Image Super-resolution
Machine Intelligence Research · 2024-12 · 21 (6) · 1062-1076
DOI: 10.1007/s11633-024-1501-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Intelligence Research, online erschienen am 20.08.2024. Verfasst von Gang Wu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 53-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Deep convolutional neural networks, particularly large models with large kernels (3 × 3 or more), have achieved significant progress in single image super-resolution (SISR) tasks. However, the heavy computational footprint of such models prevents their deployment in real-time, resource-constrained environments. Conversely, 1 × 1 convolutions have substantial computational efficiency, but struggle with aggregating local spatial representations, which is an essential capability for SISR models. In response to this dichotomy, we propose to harmonize the merits of both 3 × 3 and 1 × 1 kernels, and exploit their great potential for lightweight SISR tasks. Specifically, we propose a simple yet effective fully 1 × 1 convolutional network, named shift-Conv-based network (SCNet). By incorporating a parameter-free spatial-shift operation, the fully 1 × 1 convolutional network is equipped with a powerful representation capability and impressive computational efficiency. Extensive experiments demonstrate that SCNets, despite their fully 1 × 1 convolutional structure, consistently match or even surpass the performance of existing lightweight SR models that employ regular convolutions. The code and pretrained models can be found at https://github.com/Aitical/SCNet .
Zitieren
APA
Wu, G., Jiang, J., Jiang, K., & Liu, X. (2024). Fully 1 × 1 Convolutional Network for Lightweight Image Super-resolution. Machine Intelligence Research, 21(6), 1062-1076. https://doi.org/10.1007/s11633-024-1501-9
Vancouver
Wu G, Jiang J, Jiang K, Liu X. Fully 1 × 1 Convolutional Network for Lightweight Image Super-resolution. Machine Intelligence Research. 2024;21(6):1062-1076. doi:10.1007/s11633-024-1501-9
BibTeX
@article{Wu2024,
author = {Wu, Gang and Jiang, Junjun and Jiang, Kui and Liu, Xianming},
title = {Fully 1 × 1 Convolutional Network for Lightweight Image Super-resolution},
journal = {Machine Intelligence Research},
year = {2024},
volume = {21},
number = {6},
pages = {1062--1076},
doi = {10.1007/s11633-024-1501-9}
}
EUVIMED