Filters








89 Hits in 5.6 sec

NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results [article]

Andreas Lugmayr, Martin Danelljan, Radu Timofte, Namhyuk Ahn, Dongwoon Bai, Jie Cai, Yun Cao, Junyang Chen, Kaihua Cheng, SeYoung Chun, Wei Deng, Mostafa El-Khamy (+34 others)
2020 arXiv   pre-print
This paper reviews the NTIRE 2020 challenge on real world super-resolution. It focuses on the participating methods and final results.  ...  The challenge addresses the real world setting, where paired true high and low-resolution images are unavailable.  ...  Acknowledgements We thank the NTIRE 2020 sponsors: Huawei, Oppo, Voyage81, MediaTek, DisneyResearch|Studios, and Computer Vision Lab (CVL) ETH Zurich.  ... 
arXiv:2005.01996v1 fatcat:ewngd7chdve3fbvwis32v64ruq

NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results [article]

Kai Zhang, Shuhang Gu, Radu Timofte, Taizhang Shang, Qiuju Dai, Shengchen Zhu, Tong Yang, Yandong Guo, Younghyun Jo, Sejong Yang, Seon Joo Kim, Lin Zha (+51 others)
2020 arXiv   pre-print
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.  ...  The track had 280 registered participants, and 19 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.  ...  Acknowledgements We thank the NTIRE 2020 sponsors: HUAWEI, OPPO, Voyage81, MediaTek, DisneyResearch|Studios, and Computer Vision Lab (CVL) ETH Zurich.  ... 
arXiv:2005.01056v1 fatcat:6nwj5ilbgbgjnmd6oy435hjdhi

SimUSR: A Simple but Strong Baseline for Unsupervised Image Super-resolution [article]

Namhyuk Ahn and Jaejun Yoo and Kyung-Ah Sohn
2020 arXiv   pre-print
We submitted our method in NTIRE 2020 super-resolution challenge and won 1st in PSNR, 2nd in SSIM, and 13th in LPIPS.  ...  In this paper, we tackle a fully unsupervised super-resolution problem, i.e., neither paired images nor ground truth HR images.  ...  This work was supported by NAVER Corporation and also by the National Research Foundation of Korea grant funded by the Korea government (MSIT) (no.NRF-2019R1A2C1006608)  ... 
arXiv:2004.11020v1 fatcat:4r5xru6zzbdz3ezgucrj5yzofi

NTIRE 2020 Challenge on Image Demoireing: Methods and Results [article]

Shanxin Yuan, Radu Timofte, Ales Leonardis, Gregory Slabaugh, Xiaotong Luo, Jiangtao Zhang, Yanyun Qu, Ming Hong, Yuan Xie, Cuihua Li, Dejia Xu, Yihao Chu (+34 others)
2020 arXiv   pre-print
This paper reviews the Challenge on Image Demoireing that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2020.  ...  The methods were ranked in terms of their fidelity, measured using the peak signal-to-noise ratio (PSNR) between the ground truth clean images and the restored images produced by the participants' methods  ...  Acknowledgements We thank the NTIRE 2020 sponsors: Huawei, OPPO, Voyage81, MediaTek, DisneyResearch|Studios, and Computer Vision Lab (CVL) ETH Zurich.  ... 
arXiv:2005.03155v1 fatcat:7cob4jufzbawfafcimgtoitdk4

NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results [article]

Dario Fuoli, Zhiwu Huang, Martin Danelljan, Radu Timofte, Hua Wang, Longcun Jin, Dewei Su, Jing Liu, Jaehoon Lee, Michal Kudelski, Lukasz Bala, Dmitry Hrybov (+9 others)
2020 arXiv   pre-print
This paper reviews the NTIRE 2020 challenge on video quality mapping (VQM), which addresses the issues of quality mapping from source video domain to target video domain.  ...  The challenge includes both a supervised track (track 1) and a weakly-supervised track (track 2) for two benchmark datasets.  ...  Acknowledgements We thank the NTIRE 2020 sponsors: Huawei, Oppo, Voyage81, MediaTek, DisneyResearch|Studios, and Computer Vision Lab (CVL) ETH Zurich.  ... 
arXiv:2005.02291v3 fatcat:z5zgwpnyrveothp337xeb7yfoy

Blind Super-Resolution Kernel Estimation using an Internal-GAN [article]

Sefi Bell-Kligler, Assaf Shocher, Michal Irani
2020 arXiv   pre-print
Super resolution (SR) methods typically assume that the low-resolution (LR) image was downscaled from the unknown high-resolution (HR) image by a fixed 'ideal' downscaling kernel (e.g.  ...  We introduce "KernelGAN", an image-specific Internal-GAN, which trains solely on the LR test image at test time, and learns its internal distribution of patches.  ...  Experiments and results We evaluated our method on real LR images, as well as on 'non-ideal' synthetically generated LR images with ground-truth (both ground-truth HR images, as well as the true SR-kernels  ... 
arXiv:1909.06581v6 fatcat:plaj36fojfcp5fwuqphns4do7a

Generalized Real-World Super-Resolution through Adversarial Robustness [article]

Angela Castillo, María Escobar, Juan C. Pérez, Andrés Romero, Radu Timofte, Luc Van Gool, Pablo Arbeláez
2021 arXiv   pre-print
We perform extensive experimentation on synthetic and real-world images and empirically demonstrate that our RSR method generalizes well across datasets without re-training for specific noise priors.  ...  Real-world Super-Resolution (SR) has been traditionally tackled by first learning a specific degradation model that resembles the noise and corruption artifacts in low-resolution imagery.  ...  Acknowledgements: We thank Guillaume Jeanneret for insightful discussions on the subject.  ... 
arXiv:2108.11505v1 fatcat:irsrdqyzabc6zli3nk4a4cfi2m

Simple and Efficient Unpaired Real-world Super-Resolution using Image Statistics [article]

Kwangjin Yoon
2021 arXiv   pre-print
We test our method on the NTIRE 2020 real-world SR dataset.  ...  Our real-world SR framework consists of two GANs, one for translating HR images to LR images (degradation task) and the other for translating LR to HR (SR task).  ...  Experiments We test our method on the NTIRE 2020 real-world SR dataset [11] .  ... 
arXiv:2109.09071v1 fatcat:d7aha2nn4zba3b7i3h2rv5uztq

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
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  ...  Single image super-resolution (SISR) has played an important role in the field of image processing.  ...  2020 Real World SR challenge [173] NTIRE 2020 Real World SR challenge [173] USISResNet [129] NTIRE-2020 Real-world SR Challenge validation dataset [173] , DIV2K [151] , Flickr2k [152] , KADID  ... 
arXiv:2204.13620v1 fatcat:hlwdqith65cxrbqrnbphjz6u4u

Unfolding the Alternating Optimization for Blind Super Resolution [article]

Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tieniu Tan
2020 arXiv   pre-print
Extensive experiments on synthetic datasets and real-world images show that our model can largely outperform state-of-the-art methods and produce more visually favorable results at much higher speed.  ...  Previous methods decompose blind super resolution (SR) problem into two sequential steps: i) estimating blur kernel from given low-resolution (LR) image and ii) restoring SR image based on estimated kernel  ...  Extensive experiments on synthetic datasets and real-world images show that our model can largely outperform state-of-the art methods and produce more visually favorable results at much higher speed.  ... 
arXiv:2010.02631v4 fatcat:bil5miozmnhnvltr46l37zjuki

NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results [article]

Abdelrahman Abdelhamed, Mahmoud Afifi, Radu Timofte, Michael S. Brown, Yue Cao, Zhilu Zhang, Wangmeng Zuo, Xiaoling Zhang, Jiye Liu, Wendong Chen, Changyuan Wen, Meng Liu (+78 others)
2020 arXiv   pre-print
This paper reviews the NTIRE 2020 challenge on real image denoising with focus on the newly introduced dataset, the proposed methods and their results.  ...  The challenge is a new version of the previous NTIRE 2019 challenge on real image denoising that was based on the SIDD benchmark.  ...  Acknowledgements We thank the NTIRE 2020 sponsors: Huawei, Oppo, Voyage81, MediaTek, DisneyResearch|Studios, and Computer Vision Lab (CVL) ETH Zurich. A. Teams and  ... 
arXiv:2005.04117v1 fatcat:iwtpyxikerbqhhvkpmwghqxeke

Unpaired Image Super-Resolution using Pseudo-Supervision [article]

Shunta Maeda
2020 arXiv   pre-print
However, these methods fail to super-resolve real-world low-resolution (LR) images, for which the degradation process is much more complicated and unknown.  ...  In most studies on learning-based image super-resolution (SR), the paired training dataset is created by downscaling high-resolution (HR) images with a predetermined operation (e.g., bicubic).  ...  Acknowledgement I thank Tatsuya Nagata, Shunsuke Ono, Kazuki Sekine, Hiraku Shibuya and Yusuke Uchida for helpful comments on the manuscript.  ... 
arXiv:2002.11397v1 fatcat:xqrg7vlrzzfhheanqwmnhzuwl4

Brightness Invariant Deep Spectral Super-Resolution

Tarek Stiebel, Dorit Merhof
2020 Sensors  
Spectral reconstruction from RGB or spectral super-resolution (SSR) offers a cheap alternative to otherwise costly and more complex spectral imaging devices.  ...  The approach is independent of concrete network architectures and instead focuses on reevaluating what neural networks should actually predict.  ...  Average reconstruction metrics over the test set, which equals the official validation split of the NTIRE 2020 challenge on spectral reconstruction [11] .  ... 
doi:10.3390/s20205789 pmid:33066187 pmcid:PMC7602104 fatcat:tyixs2hconantiaab44iykffsu

Blind Image Super-Resolution: A Survey and Beyond [article]

Anran Liu, Yihao Liu, Jinjin Gu, Yu Qiao, Chao Dong
2021 arXiv   pre-print
Blind image super-resolution (SR), aiming to super-resolve low-resolution images with unknown degradation, has attracted increasing attention due to its significance in promoting real-world applications  ...  Last but not least, a comparison among different methods is provided with detailed analysis on their merits and demerits using both synthetic and real testing images.  ...  each kind of methods. 1: Details of challenges on blind image super-resolution.  ... 
arXiv:2107.03055v1 fatcat:65d6fogzyjf2tly4gaacphpju4

Real-World Single Image Super-Resolution: A Brief Review [article]

Honggang Chen, Xiaohai He, Linbo Qing, Yuanyuan Wu, Chao Ren, Ce Zhu
2021 arXiv   pre-print
This article aims to make a comprehensive review on real-world single image super-resolution (RSISR).  ...  Recent studies show that simulation results on synthetic data usually overestimate the capacity to super-resolve real-world images.  ...  [98] take this idea one step further and develop an effective degradation framework using various realistic blur kernels and noise distributions, winning the NTIRE 2020 Challenge on Real-World Image  ... 
arXiv:2103.02368v1 fatcat:fesf6ercffdxdg7jx3mda6nkri
« Previous Showing results 1 — 15 out of 89 results