☆ 4.6 Article

Frequency-Based Enhancement Network for Efficient Super-Resolution

IEEE ACCESS (2022)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Artificial Intelligence

Multi-attention augmented network for single image super-resolution

Rui Chen et al.

Summary: This paper proposes a multi-attention augmented network, including content-aware module, orientation-aware module, and position-aware module, to enhance multi-scale feature learning and fusion, extract multi-orientation features, and adaptively fuse through channel attention mechanism, thus improving the reconstruction accuracy and perceptual quality of image super-resolution.

PATTERN RECOGNITION (2022)

添加到收藏夹

Article Automation & Control Systems

Cascading and Enhanced Residual Networks for Accurate Single-Image Super-Resolution

Rushi Lan et al.

Summary: This article addresses the challenges of high parameter and complex structure in CNN models for SISR by introducing novel local wider residual blocks (LWRBs) and various strategies. The proposed cascading residual network (CRN) and enhanced residual network (ERN) achieve superior results compared to advanced methods, while effectively utilizing low-level features.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

添加到收藏夹

Article Automation & Control Systems

MADNet: A Fast and Lightweight Network for Single-Image Super Resolution

Rushi Lan et al.

Summary: In this article, a dense lightweight network named MADNet is proposed for stronger multiscale feature expression and feature correlation learning. With the development of a residual multiscale module with an attention mechanism and a dual residual-path block, the model demonstrates superior performance while utilizing fewer multiadds and parameters.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Image super -resolution via channel attention and spatial graph convolutional network

Yue Yang et al.

Summary: In this work, a channel attention and spatial graph convolutional network (CASGCN) is proposed for more powerful feature obtaining and feature correlations modeling by incorporating global spatial and channel inter-dependencies. CASGCN utilizes channel and spatial branches to learn the representation of each image pixel, using attention mechanism and spatial-aware graph to extract informative features and model global self-similar information. The adjacency matrix in spatial-aware graph is dynamically generated via the Gram matrix to model global correlations between pixels and is shared across the whole network without auxiliary parameters. Extensive experiments demonstrate the effectiveness of CASGCN in single image superresolution tasks.

PATTERN RECOGNITION (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Single-Image super-resolution-When model adaptation matters

Yudong Liang et al.

Summary: Deep learning has made significant advancements in single-image super-resolution, utilizing deep network design and external prior modeling. This study introduces a specific deep model to enhance low-resolution images and improve PSNR. Moreover, the approach is particularly suitable for images with repetitive structures or high resolutions.

PATTERN RECOGNITION (2021)

添加到收藏夹

Article Computer Science, Information Systems

Multi-Branch Neural Architecture Search for Lightweight Image Super-Resolution

Joon Young Ahn et al.

Summary: An improved SISR search method is proposed in this paper, which significantly reduces design time by applying weight-sharing scheme and multi-branch structure, resulting in better performance in texture region reconstruction.

IEEE ACCESS (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

OverNet: Lightweight Multi-Scale Super-Resolution with Overscaling Network

Parichehr Behjati et al.

Summary: OverNet is a deep yet lightweight convolutional network that addresses the computational complexity and memory requirements in CNN-based SR methods by solving SISR at arbitrary scale factors with a single model. The introduction of a lightweight feature extractor, model-agnostic reconstruction module, and multi-scale loss function enables generalization and optimization across various scales, outperforming previous state-of-the-art approaches in standard benchmarks.

2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021 (2021)

添加到收藏夹

Article Computer Science, Information Systems

Enhanced Dense Space Attention Network for Super-Resolution Construction From Single Input Image

Yoong Khang Ooi et al.

Summary: This paper introduces a method of using CNN for single-image super-resolution construction and proposes the Enhanced Dense Space Attention Network (EDSAN) model to solve the vanishing-gradient problem, improve accuracy, and reduce model running time. By combining dense connections, residual networks, convolutional block attention modules, and multiscale blocks, the model has achieved good results in image super-resolution tasks.

IEEE ACCESS (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

LiNet: A Lightweight Network for Image Super Resolution

Armin Mehri et al.

Summary: LiNet is a new lightweight network that enhances technical efficiency in lightweight super resolution by introducing a Compact Dense Module to extract meaningful information and better leverage multi-level representations before the upsampling stage. Experimental results show that LiNet achieves favorable performance compared to lightweight state-of-the-art methods on benchmark datasets.

2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) (2021)

添加到收藏夹

Article Computer Science, Information Systems

RBDN: Residual Bottleneck Dense Network for Image Super-Resolution

Zeyu An et al.

Summary: The article introduces a new model RBDN for single-image super-resolution, which improves visual quality by enhancing network architecture, adversarial loss, and perceptual loss. The model utilizes dense cascading connections and bottleneck structures to better utilize features between layers, reducing the number of parameters; by removing the BN layer, employing the ELU function, and improving the loss function to enhance training stability and the realism of high-resolution images.

IEEE ACCESS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Light Weight IBP Deep Residual Network for Image Super Resolution

Hai Lin et al.

Summary: The study proposes a lightweight network model that applies the iterative back projection mechanism to reduce the dimensionality of input image features, achieving better accuracy and speed in image super resolution reconstruction.

IEEE ACCESS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Lightweight Attended Multi-Scale Residual Network for Single Image Super-Resolution

Yitong Yan et al.

Summary: The paper introduces a lightweight attended multi-scale residual network (LAMRN) which achieves competitive performance against the state-of-the-art methods by utilizing attended multi-scale residual block (AMSRB) and double-attention fusion (DAF) block to extract and fuse features efficiently.

IEEE ACCESS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Single Image Super-Resolution by Residual Recovery Based on an Independent Deep Convolutional Network

Fei Wang et al.

Summary: In this paper, an independent neural network for single image super-resolution by residual recovery is proposed, which successfully enhances low-resolution images to high resolution by training the mapping between image residuals and ground-truth residuals. Experimental results demonstrate the effectiveness of the proposed method in terms of visual and quantitative performance.

IEEE ACCESS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Hierarchical dense recursive network for image super-resolution

Kui Jiang et al.

PATTERN RECOGNITION (2020)

添加到收藏夹

Article Chemistry, Analytical

Deeply Recursive Low- and High-Frequency Fusing Networks for Single Image Super-Resolution

Cheng Yang et al.

SENSORS (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

Channel-Wise and Spatial Feature Modulation Network for Single Image Super-Resolution

Yanting Hu et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2020)

添加到收藏夹

Article Computer Science, Information Systems

Frequency Separation Network for Image Super-Resolution

Shanshan Li et al.

IEEE ACCESS (2020)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Embedded Block Residual Network: A Recursive Restoration Model for Single-Image Super-Resolution

Yajun Qiu et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

ODE-inspired Network Design for Single Image Super-Resolution

Xiangyu He et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Densely Connected Pyramid Dehazing Network

He Zhang et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

添加到收藏夹

Article Computer Science, Information Systems

Sketch-based manga retrieval using manga109 dataset

Yusuke Matsui et al.

MULTIMEDIA TOOLS AND APPLICATIONS (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study

Eirikur Agustsson et al.

2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution

Wei-Sheng Lai et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Densely Connected Convolutional Networks

Gao Huang et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

A Deep Convolutional Neural Network with Selection Units for Super-Resolution

Jae-Seok Choi et al.

2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Christian Ledig et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Image Super-Resolution Using Deep Convolutional Networks

Chao Dong et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2016)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Unsupervised Simultaneous Orthogonal Basis Clustering Feature Selection

Dongyoon Han et al.

2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2015)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A Statistical Prediction Model Based on Sparse Representations for Single Image Super-Resolution

Tomer Peleg et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2014)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding

Marco Bevilacqua et al.

PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2012 (2012)

添加到收藏夹

Article Computer Science, Software Engineering

Image and Video Upscaling from Local Self-Examples

Gilad Freedman et al.

ACM TRANSACTIONS ON GRAPHICS (2011)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Contour Detection and Hierarchical Image Segmentation

Pablo Arbelaez et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2011)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Image quality assessment: From error visibility to structural similarity

Z Wang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2004)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.