Results 11 to 20 of about 18,250,440 (204)

Single Image Super-Resolution [PDF]

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal, 2019
Super-Resolution (SR) of a single image is a classic problem in computer vision. The goal of image super-resolution is to produce a high-resolution image from a low-resolution image. This paper presents a popular model, super-resolution convolutional neural network (SRCNN), to solve this problem. This paper also examines an improvement to SRCNN using a
Song, Yujing, Yujing Song
openaire   +3 more sources

Single image super resolution with high resolution dictionary

2011 18th IEEE International Conference on Image Processing, 2011
Image super resolution (SR) is a technique to estimate or synthesize a high resolution (HR) image from one or several low resolution (LR) images. This paper proposes a novel framework for single image super resolution based on sparse representation with high resolution dictionary. Unlike the previous methods, the training set is constructed from the HR
Guangwu Mu, Xinbo Gao 0001, Kaibing Zhang, Xuelong Li 0001, Dacheng Tao   +4 more
core   +3 more sources

Anchored neighborhood deep network for single-image super-resolution

EURASIP Journal on Image and Video Processing, 2018
Real-time image and video processing is a challenging problem in smart surveillance applications. It is necessary to trade off between high frame rate and high resolution to meet the limited bandwidth requirement in many specific applications.
Wuzhen Shi, Shaohui Liu, Feng Jiang, Debin Zhao, Zhihong Tian   +4 more
doaj   +2 more sources

Neighborhood Issue in Single-Frame Image Super-Resolution [PDF]

2005 IEEE International Conference on Multimedia and Expo, 2005
Super-resolution is the problem of generating one or a set of high-resolution images from one or a sequence of low-resolution frames. Most methods have been proposed for super-resolution based on multiple low resolution images of the same scene, which is called multiple-frame super-resolution.
Xu (Kevin) Su, Qi Tian 0001, Qing Xue, Nicu Sebe, Jingsheng Ma   +4 more
openaire   +4 more sources

Colorization for Single Image Super Resolution

, 2010
This paper introduces a new procedure to handle color in single image super resolution (SR). Most existing SR techniques focus primarily on enforcing image priors or synthesizing image details; less attention is paid to the final color assignment. As a result, many existing SR techniques exhibit some form of color aberration in the final upsampled ...
Shuaicheng Liu, Michael S. Brown, Seon Joo Kim, Yu-Wing Tai   +3 more
core   +3 more sources

Single Image Super-Resolution

CoRR, 2021
This study presents a chronological overview of the single image super-resolution problem. We first define the problem thoroughly and mention some of the serious challenges. Then the problem formulation and the performance metrics are defined. We give an overview of the previous methods relying on reconstruction based solutions and then continue with ...
Baran Ataman, Mert Seker, David McKee
openaire   +2 more sources

Transformer for Single Image Super-Resolution

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022
Accepted by CVPR workshop ...
Zhisheng Lu, Juncheng Li 0008, Hong Liu, Chaoyan Huang, Linlin Zhang, Tieyong Zeng   +5 more
openaire   +3 more sources

Benefiting from Multitask Learning to Improve Single Image Super-Resolution [PDF]

, 2020
Despite significant progress toward super resolving more realistic images by deeper convolutional neural networks (CNNs), reconstructing fine and natural textures still remains a challenging problem.
Thiran, Jean-Philippe, Musat, Claudiu, Marti, Urs-Viktor, Basler, Max, Rad, Mohammad Saeed, Bozorgtabar, Behzad, Ekenel, Hazim Kemal, Behzad Bozorgtabar, Claudiu Musat, Urs-Viktor Marti, Max Basler, Jean-Philippe Thiran, Mohammad Saeed Rad, Hazim Kemal Ekenel, Ekenel, Hazım Kemal   +14 more
core   +1 more source

Deep Super-Resolution Network for Single Image Super-Resolution with Realistic Degradations [PDF]

Proceedings of the 13th International Conference on Distributed Smart Cameras, 2019
Single Image Super-Resolution (SISR) aims to generate a high-resolution (HR) image of a given low-resolution (LR) image. The most of existing convolutional neural network (CNN) based SISR methods usually take an assumption that a LR image is only bicubicly down-sampled version of an HR image. However, the true degradation (i.e.
UMER, RAO MUHAMMAD, Foresti G. L., Micheloni C.   +2 more
openaire   +4 more sources

Skip-Concatenated Image Super-Resolution Network for Mobile Devices

IEEE Access, 2023
Single-image super-resolution technology has been widely studied in various applications to improve the quality and resolution of degraded images acquired from noise-sensitive low-resolution sensors.
Ganzorig Gankhuyag, Jingang Huh, Myeongkyun Kim, Kihwan Yoon, Hyeoncheol Moon, Seungho Lee, Jinwoo Jeong, Sungjei Kim, Yoonsik Choe   +8 more
doaj   +1 more source