Bidirectional scale-aware upsampling network for arbitrary-scale video super-resolution

被引:1
|
作者
Luo, Laigan [1 ]
Yi, Benshun [1 ]
Wang, Zhongyuan [2 ]
He, Zheng [2 ]
Zhu, Chao [1 ]
机构
[1] Wuhan Univ, Elect Informat Sch, Wuhan 430072, Peoples R China
[2] Wuhan Univ, Natl Engn Res Ctr Multimedia Software, Sch Comp Sci, Wuhan 430072, Peoples R China
基金
中国国家自然科学基金;
关键词
Video super -resolution; Arbitrary -scale factor; Bidirectional module; Upsampling module; IMAGE SUPERRESOLUTION;
D O I
10.1016/j.imavis.2024.105116
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The performance of video super-resolution (VSR) has significantly improved. However, the current methods only focus on a single scale factor, treating the VSR of different scale factors independently and disregarding video super-resolution of arbitrary-scale factors. To address this issue, we propose a model, the Bidirectional ScaleAware Upsampling Network for Arbitrary-Scale Video Super-Resolution, which eliminates the need for multiple models for various scale factors. We design a Bidirectional Scale-Aware Upsampling module in the proposed model, consisting of a Bidirectional Scale-Aware Module (BSAM) and a Spatial Pyramid Upsampling section. The BSAM extracts feature for various scale factors and allows feature information of different scales to interact bidirectionally. Additionally, we propose a Spatial Pyramid Loss that optimizes the network based on upsampling and maps the results of different scales to a unified spatial set to find the arbitrary-scale factor's loss. Along with this, we introduce an Explicit Feature Pyramid module, which uses Spatial Pyramid Upsampling to learn arbitrary-scale factor details explicitly. Finally, we demonstrate the extensibility of the model through a VSR algorithm integration with the Bidirectional Scale-Aware Upsampling, ensuring high-resolution results of arbitrary-scale factors without affecting the performance. Our comprehensive experiments on public benchmarks show promising results for video super-resolution of arbitrary-scale factors.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors
    Shang, Wei
    Ren, Dongwei
    Zhang, Wanying
    Fang, Yuming
    Zuo, Wangmeng
    Ma, Kede
    COMPUTER VISION-ECCV 2024, PT LVII, 2025, 15115 : 73 - 90
  • [2] SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network
    Li, Zekun
    Liu, Hongying
    Shang, Fanhua
    Liu, Yuanyuan
    Wan, Liang
    Feng, Wei
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 4, 2024, : 3288 - 3296
  • [3] Scale-Aware Frequency Attention network for super-resolution
    Yu, Wei
    Li, Zonglin
    Liu, Qinglin
    Jiang, Feng
    Guo, Changyong
    Zhang, Shengping
    NEUROCOMPUTING, 2023, 554
  • [4] UNCERTAINTY AWARE IMPLICIT IMAGE FUNCTION FOR ARBITRARY-SCALE SUPER-RESOLUTION
    Jena, Swastik
    Panda, Saptarshi
    Balabantaray, Bunil Kumar
    Nayak, Rajashree
    2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 2440 - 2444
  • [5] Scale-Aware Distillation Network for Lightweight Image Super-Resolution
    Lu, Haowei
    Lu, Yao
    Li, Gongping
    Sun, Yanbei
    Wang, Shunzhou
    Li, Yugang
    PATTERN RECOGNITION AND COMPUTER VISION,, PT III, 2021, 13021 : 128 - 139
  • [6] Enhanced dual branches network for arbitrary-scale image super-resolution
    Li, Guangping
    Xiao, Huanling
    Liang, Dingkai
    ELECTRONICS LETTERS, 2023, 59 (01)
  • [7] Deformable Convolution Alignment and Dynamic Scale-Aware Network for Continuous-Scale Satellite Video Super-Resolution
    Ni, Ning
    Zhang, Libao
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 17
  • [8] Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution
    Chen, Hao-Wei
    Xu, Yu-Syuan
    Hong, Min-Fong
    Tsai, Yi-Min
    Kuo, Hsien-Kai
    Lee, Chun-Yi
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 18257 - 18267
  • [9] Arbitrary-Scale Image Super-Resolution via Degradation Perception
    Wan, Wenbo
    Wang, Zezhu
    Wang, Zhiyan
    Gu, Lingchen
    Sun, Jiande
    Wang, Qiang
    IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING, 2024, 10 : 666 - 676
  • [10] Activating More Information in Arbitrary-Scale Image Super-Resolution
    Zhao, Yaoqian
    Teng, Qizhi
    Chen, Honggang
    Zhang, Shujiang
    He, Xiaohai
    Li, Yi
    Sheriff, Ray E.
    IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 26 : 7946 - 7961