Fully $1\times1$ Convolutional Network for Lightweight Image Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Gang, Jiang, Junjun, Jiang, Kui, Liu, Xianming
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914710047162368
author Wu, Gang
Jiang, Junjun
Jiang, Kui
Liu, Xianming
author_facet Wu, Gang
Jiang, Junjun
Jiang, Kui
Liu, Xianming
contents Deep models have achieved significant process on single image super-resolution (SISR) tasks, in particular large models with large kernel ($3\times3$ or more). However, the heavy computational footprint of such models prevents their deployment in real-time, resource-constrained environments. Conversely, $1\times1$ convolutions bring substantial computational efficiency, but struggle with aggregating local spatial representations, an essential capability to SISR models. In response to this dichotomy, we propose to harmonize the merits of both $3\times3$ and $1\times1$ kernels, and exploit a great potential for lightweight SISR tasks. Specifically, we propose a simple yet effective fully $1\times1$ convolutional network, named Shift-Conv-based Network (SCNet). By incorporating a parameter-free spatial-shift operation, it equips the fully $1\times1$ convolutional network with powerful representation capability while impressive computational efficiency. Extensive experiments demonstrate that SCNets, despite its fully $1\times1$ convolutional structure, consistently matches or even surpasses the performance of existing lightweight SR models that employ regular convolutions. The code and pre-trained models can be found at https://github.com/Aitical/SCNet.
format Preprint
id arxiv_https___arxiv_org_abs_2307_16140
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Fully $1\times1$ Convolutional Network for Lightweight Image Super-Resolution
Wu, Gang
Jiang, Junjun
Jiang, Kui
Liu, Xianming
Computer Vision and Pattern Recognition
Artificial Intelligence
Deep models have achieved significant process on single image super-resolution (SISR) tasks, in particular large models with large kernel ($3\times3$ or more). However, the heavy computational footprint of such models prevents their deployment in real-time, resource-constrained environments. Conversely, $1\times1$ convolutions bring substantial computational efficiency, but struggle with aggregating local spatial representations, an essential capability to SISR models. In response to this dichotomy, we propose to harmonize the merits of both $3\times3$ and $1\times1$ kernels, and exploit a great potential for lightweight SISR tasks. Specifically, we propose a simple yet effective fully $1\times1$ convolutional network, named Shift-Conv-based Network (SCNet). By incorporating a parameter-free spatial-shift operation, it equips the fully $1\times1$ convolutional network with powerful representation capability while impressive computational efficiency. Extensive experiments demonstrate that SCNets, despite its fully $1\times1$ convolutional structure, consistently matches or even surpasses the performance of existing lightweight SR models that employ regular convolutions. The code and pre-trained models can be found at https://github.com/Aitical/SCNet.
title Fully $1\times1$ Convolutional Network for Lightweight Image Super-Resolution
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2307.16140