光学精密工程2024，Vol.32Issue(16)：2564-2576,13.DOI:10.37188/OPE.20243216.2564
基于混合时空卷积的轻量级视频超分辨率重建
Lightweight video super-resolution based on hybrid spatio-temporal convolution
摘要
Abstract
Addressing the issue of high computational complexity and limited extraction of spatio-temporal features in 3D convolutional neural networks for video super-resolution tasks,this paper introduced a novel lightweight video super-resolution reconstruction network based on hybrid spatio-temporal convolution.Firstly,a hybrid spatio-temporal convolution-based module was proposed to realize the enhancement of the spatio-temporal feature extraction capability of the network as well as reduction of the computational complexity.Then,a similarity-based selective feature fusion module was proposed to further enhance the extraction capability of relevant features.Lastly,a motion compensation module based on the attention mechanism was designed to mitigate the effects of erroneous feature fusion to a certain extent.The experi-mental results demonstrate that the proposed network can achieve a favorable balance between video super-resolution performance and network complexity,and the 4-fold super-resolution reaches 8 frames per sec-ond on the benchmark dataset SPMCS-11.The proposed network meets the requirements for fast and ac-curate reasoning operations on edge devices.关键词
视频超分辨率/深度学习/三维卷积神经网络/特征融合Key words
video super-resolution/deep learning/3D Convolutional Neural Network/feature fusion分类
计算机与自动化引用本文复制引用
夏振平,陈豪,张宇宁,程成,胡伏原..基于混合时空卷积的轻量级视频超分辨率重建[J].光学精密工程,2024,32(16):2564-2576,13.基金项目
国家自然科学基金资助项目(No.62002254) （No.62002254）
江苏省自然科学基金资助项目(No.BK20200988) （No.BK20200988）
苏州市科技计划项目(No.SNG-2023002) （No.SNG-2023002）
