Learning Local Distribution for Extremely Efficient Single-Image Super-Resolution
Achieving balance between efficiency and performance is a key problem for convolution neural network (CNN)-based single-image super-resolution (SISR) algorithms. Existing methods tend to directly output high-resolution (HR) pixels or residuals to reconstruct the HR image and focus a lot of attention...
Main Authors: | Wei Wu, Wen Xu, Bolun Zheng, Aiai Huang, Chenggang Yan |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-04-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/11/9/1348 |
Similar Items
-
From Local to Global: Efficient Dual Attention Mechanism for Single Image Super-Resolution
by: Pei Zhang, et al.
Published: (2021-01-01) -
Feature-Domain Adaptive Contrastive Distillation for Efficient Single Image Super-Resolution
by: Hyeon-Cheol Moon, et al.
Published: (2023-01-01) -
Extreme Low-Resolution Activity Recognition Using a Super-Resolution-Oriented Generative Adversarial Network
by: Mingzheng Hou, et al.
Published: (2021-06-01) -
Burst-Enhanced Super-Resolution Network (BESR)
by: Jiaao Li, et al.
Published: (2024-03-01) -
Single Image Super-Resolution Based on Multi-Scale Competitive Convolutional Neural Network
by: Xiaofeng Du, et al.
Published: (2018-03-01)