Filters








105 Hits in 8.9 sec

NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results

Radu Timofte, Eirikur Agustsson, Luc Van Gool, Ming-Hsuan Yang, Lei Zhang, Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, Kyoung Mu Lee, Xintao Wang, Yapeng Tian (+65 others)
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results.  ...  Each competition had ∼ 100 registered participants and 20 teams competed in the final testing phase. They gauge the state-of-the-art in single image super-resolution.  ...  Acknowledgements We thank the NTIRE 2017 sponsors: NVIDIA Corp., SenseTime Group Ltd., Twitter Inc., Google Inc., and ETH Zurich. A.19. UESTC-kb545 team  ... 
doi:10.1109/cvprw.2017.149 dblp:conf/cvpr/TimofteAG0ZLSKN17 fatcat:myclcf7hzve2zetlutq64pqeyu

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

Eirikur Agustsson, Radu Timofte
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
We conclude that the NTIRE 2017 challenge pushes the state-ofthe-art in single-image super-resolution, reaching the best results to date on the popular Set5, Set14, B100, Urban100 datasets and on our newly  ...  This paper introduces a novel large dataset for examplebased single image super-resolution and studies the stateof-the-art as emerged from the NTIRE 2017 challenge.  ...  Acknowledgements We thank the NTIRE 2017 sponsors: NVIDIA Corp., SenseTime Group Ltd., Twitter Inc., Google Inc., and ETH Zurich.  ... 
doi:10.1109/cvprw.2017.150 dblp:conf/cvpr/AgustssonT17 fatcat:hos2snnpivccrgiku3b4gnwk3q

AIM 2019 Challenge on Constrained Super-Resolution: Methods and Results [article]

Kai Zhang, Shuhang Gu, Radu Timofte, Zheng Hui, Xiumei Wang, Xinbo Gao, Dongliang Xiong, Shuai Liu, Ruipeng Gang, Nan Nan, Chenghua Li, Xueyi Zou (+16 others)
2019 arXiv   pre-print
This paper reviews the AIM 2019 challenge on constrained example-based single image super-resolution with focus on proposed solutions and results. The challenge had 3 tracks.  ...  Each track had an average of 64 registered participants, and 12 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.  ...  Teams and affiliations AIM2019 team  ... 
arXiv:1911.01249v1 fatcat:zcenvwesgjeqzczrslqm7a5pqa

Efficient Module Based Single Image Super Resolution for Multiple Problems

Dongwon Park, Kwanyoung Kim, Se Young Chun
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Example based single image super resolution (SR) is a fundamental task in computer vision.  ...  In this article, we propose efficient module based single image SR networks (EMBSR) and tackle multiple SR problems in NTIRE 2018 SR challenge by recycling trained networks.  ...  for NTIRE 2018 challenge on super-resolution [18] .  ... 
doi:10.1109/cvprw.2018.00133 dblp:conf/cvpr/ParkKC18 fatcat:7az3tgeqffhszp2jqi72sgwjua

Unsupervised Image Super-Resolution with an Indirect Supervised Path [article]

Zhen Han, Enyan Dai, Xu Jia, Xiaoying Ren, Shuaijun Chen, Chunjing Xu, Jianzhuang Liu, Qi Tian
2019 arXiv   pre-print
The proposed method is evaluated on both NTIRE 2017 and 2018 challenge datasets and achieves favorable performance against supervised methods.  ...  The task of single image super-resolution (SISR) aims at reconstructing a high-resolution (HR) image from a low-resolution (LR) image.  ...  The proposed method is evaluated on both NTIRE 2017 and 2018 challenge datasets and achieves comparable performance to supervised methods. Related Work Deep learning based image super-resolution.  ... 
arXiv:1910.02593v2 fatcat:fzdh5sjk2nbkpc7fdgcpkvrpoq

Balanced Two-Stage Residual Networks for Image Super-Resolution

Yuchen Fan, Honghui Shi, Jiahui Yu, Ding Liu, Wei Han, Haichao Yu, Zhangyang Wang, Xinchao Wang, Thomas S. Huang
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
We evaluated our models on the New Trends in Image Restoration and Enhancement workshop and challenge on image super-resolution (NTIRE SR 2017).  ...  In this paper, balanced two-stage residual networks (BT-SRN) are proposed for single image super-resolution.  ...  method is evaluated in the super-resolution challenge of NTIRE 2017 [33] .  ... 
doi:10.1109/cvprw.2017.154 dblp:conf/cvpr/FanSYLHYWWH17 fatcat:civz7z2ogvfbzn6cbrkfinjywa

Multi-scale deep neural networks for real image super-resolution [article]

Shangqi Gao, Xiahai Zhuang
2019 arXiv   pre-print
Single image super-resolution (SR) is extremely difficult if the upscaling factors of image pairs are unknown and different from each other, which is common in real image SR.  ...  According to the preliminary results of NTIRE 2019 image SR challenge, our team (ZXHresearch@fudan) ranks 21-st among all participants.  ...  For a given upscaling factor, the results of NTIRE 2017 image SR challenge showed that the learning-based methods perform robust when the input images are noise free [22] .  ... 
arXiv:1904.10698v1 fatcat:jdrbcz7egze6daqlussy36adyu

Image Super Resolution Based on Fusing Multiple Convolution Neural Networks

Haoyu Ren, Mostafa El-Khamy, Jungwon Lee
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In this paper, we focus on constructing an accurate super resolution system based on multiple Convolution Neural Networks (CNNs).  ...  We also discuss other network fusion schemes, including Pixel-Wise network Fusion (PWF) and Progressive Network Fusion (PNF). The experimental results show that the CNF outperforms PWF and PNF.  ...  Most modern single image superresolution methods rely on machine learning techniques. These methods focus on learning the relationship between LR and HR image patches.  ... 
doi:10.1109/cvprw.2017.142 dblp:conf/cvpr/RenEL17 fatcat:shncx4lihbbz5bo3fg4q7q7z2e

Self Super-Resolution for Magnetic Resonance Images using Deep Networks [article]

Can Zhao, Aaron Carass, Blake E. Dewey, Jerry L. Prince
2018 arXiv   pre-print
As an ill-posed problem, state-of-the-art super-resolution methods rely on the presence of external/training atlases to learn the transform from low resolution~(LR) images to high resolution~(HR) images  ...  The trained network is applied to the original input image to estimate the HR image. Our SSR result shows a significant improvement on through-plane resolution compared to competing SSR methods.  ...  In contrast, exsiting single image self super-resolution (SSR) methods [9] [10] [11] downsample the LR image to create a lower resolution (LR 2 ) image and learn the mapping from LR 2 to LR; and subsequently  ... 
arXiv:1802.09431v1 fatcat:v3xl4bden5e5di47ptqbbjnscq

Pixel-Aware Deep Function-Mixture Network for Spectral Super-Resolution

Lei Zhang, Zhiqiang Lang, Peng Wang, Wei Wei, Shengcai Liao, Ling Shao, Yanning Zhang
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Spectral super-resolution (SSR) aims at generating a hyperspectral image (HSI) from a given RGB image.  ...  Experimental results on three benchmark HSI datasets demonstrate the superiority of the proposed method.  ...  Recovered spectra form the super-resolution results of the proposed method on three example images chosen from three datasets.  ... 
doi:10.1609/aaai.v34i07.6978 fatcat:hdggxvkh65asbpbaadcv73pmoa

Image Super-Resolution via Dual-State Recurrent Networks [article]

Wei Han, Shiyu Chang, Ding Liu, Mo Yu, Michael Witbrock, Thomas S. Huang
2018 arXiv   pre-print
Advances in image super-resolution (SR) have recently benefited significantly from rapid developments in deep neural networks.  ...  Extensive quantitative and qualitative evaluations on benchmark datasets and on a recent challenge demonstrate that the proposed DSRN performs favorably against state-of-the-art algorithms in terms of  ...  Trends in Image Restoration and Enhancement workshop and challenge on image super-resolution (NTIRE SR 2017)" [1] .  ... 
arXiv:1805.02704v1 fatcat:q5hr4do2cnfhreqhf5xtyzmnzq

New Techniques for Preserving Global Structure and Denoising with Low Information Loss in Single-Image Super-Resolution [article]

Yijie Bei, Alex Damian, Shijia Hu, Sachit Menon, Nikhil Ravi, Cynthia Rudin
2018 arXiv   pre-print
This work identifies and addresses two important technical challenges in single-image super-resolution: (1) how to upsample an image without magnifying noise and (2) how to preserve large scale structure  ...  (Realistic difficult) in the 2018 NTIRE Super-Resolution Challenge.  ...  Ntire 2018 challenge on single image superresolution: Methods and results. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2018. [14] R. Tsai.  ... 
arXiv:1805.03383v2 fatcat:ytogw2jrnze73ifnndpwsjkuay

Understanding Deformable Alignment in Video Super-Resolution [article]

Kelvin C.K. Chan, Xintao Wang, Ke Yu, Chao Dong, Chen Change Loy
2020 arXiv   pre-print
video super-resolution.  ...  We further demonstrate through experiments that the increased diversity in deformable alignment yields better-aligned features, and hence significantly improves the quality of video super-resolution output  ...  NTIRE 2019 Challenge on Video Deblurring Convolutional Network for Image Super-resolution. In ECCV. and Super-Resolution: Dataset and Study. In CVPRW.  ... 
arXiv:2009.07265v1 fatcat:pwxa6xza75fqzp34czzg5fqu3q

Generative Adversarial Networks for Image Super-Resolution: A Survey [article]

Chunwei Tian, Xuanyu Zhang, Jerry Chun-Wen Lin, Wangmeng Zuo, Yanning Zhang
2022 arXiv   pre-print
Single image super-resolution (SISR) has played an important role in the field of image processing.  ...  Then, we analyze motivations, implementations and differences of GANs based optimization methods and discriminative learning for image super-resolution in terms of supervised, semi-supervised and unsupervised  ...  Most of GANs can deal with a single task, i.e., image super-resolution and synthetic noisy image super-resolution, etc.  ... 
arXiv:2204.13620v1 fatcat:hlwdqith65cxrbqrnbphjz6u4u

A Deep Journey into Super-resolution: A survey [article]

Saeed Anwar, Salman Khan, Nick Barnes
2020 arXiv   pre-print
single image super-resolution.  ...  In this exposition, we extensively compare 30+ state-of-the-art super-resolution Convolutional Neural Networks (CNNs) over three classical and three recently introduced challenging datasets to benchmark  ...  Two important challenges are listed below. NTIRE To benchmark, the single-image super-resolution, NTIRE 1 (New Trends in Image Restoration and Enhancement) [50] challenge was introduced in 2017.  ... 
arXiv:1904.07523v3 fatcat:ovihxjadfja55hrytvhggj5c6q
« Previous Showing results 1 — 15 out of 105 results