DIV8K: DIVerse 8K Resolution Image Dataset

Gu, Shuhang; Lugmayr, Andreas; Danelljan, Martin; Fritsche, Manuel; Lamour, Julien; Timofte, Radu

doi:10.1109/iccvw.2019.00435

Cited by 64 publications

(29 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specially, FL-MISR is evaluated for real-time CT imaging based on the synthetic and real-world CT measurements. Besides, the application of FL-MISR on natural images is evaluated using the public dataset DIV8K [36].…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Furthermore, since the supervised learning scheme requires the ground truth (GT) HR images during the training phase, the performance of the trained model will be limited by the available quality of the GT acquired in practice. It is especially true for CT imaging due to the lack of publicly available high-quality HR datasets like DIV8K [36] for natural images.…”

Section: Deep Learning-based Methodsmentioning

confidence: 99%

“…Since the distributed optimization of FL-MISR is based on data parallelism, FL-MISR is not limited to a certain application. We evaluate the proposed FL-MISR on natural images using the public dataset DIV8K [36]. Particularly, we randomly selected 7 natural images with the vertical or horizontal resolution ranging from 1920 to 5760 pixels as the GT.…”

Section: Evaluation On Natural Imagesmentioning

confidence: 99%

See 2 more Smart Citations

FL-MISR: fast large-scale multi-image super-resolution for computed tomography based on multi-GPU acceleration

Sun

Tran

Guhathakurta

et al. 2021

J Real-Time Image Proc

View full text Add to dashboard Cite

Multi-image super-resolution (MISR) usually outperforms single-image super-resolution (SISR) under a proper inter-image alignment by explicitly exploiting the inter-image correlation. However, the large computational demand encumbers the deployment of MISR in practice. In this work, we propose a distributed optimization framework based on data parallelism for fast large-scale MISR using multi-GPU acceleration named FL-MISR. The scaled conjugate gradient (SCG) algorithm is applied to the distributed subfunctions and the local SCG variables are communicated to synchronize the convergence rate over multi-GPU systems towards a consistent convergence. Furthermore, an inner-outer border exchange scheme is performed to obviate the border effect between neighboring GPUs. The proposed FL-MISR is applied to the computed tomography (CT) system by super-resolving the projections acquired by subpixel detector shift. The SR reconstruction is performed on the fly during the CT acquisition such that no additional computation time is introduced. FL-MISR is extensively evaluated from different aspects and experimental results demonstrate that FL-MISR effectively improves the spatial resolution of CT systems in modulation transfer function (MTF) and visual perception. Comparing to a multi-core CPU implementation, FL-MISR achieves a more than 50$$\times$$ × speedup on an off-the-shelf 4-GPU system.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Deep Learning-based Methodsmentioning

confidence: 99%

Section: Evaluation On Natural Imagesmentioning

confidence: 99%

See 1 more Smart Citation

FL-MISR: fast large-scale multi-image super-resolution for computed tomography based on multi-GPU acceleration

Sun

Tran

Guhathakurta

et al. 2021

J Real-Time Image Proc

View full text Add to dashboard Cite

show abstract

“…The clean images are sampled or cropped from existing datasets, including DeepJoint [16], HDR+ [20], and DIV8K [18]. The corresponding moire images are generated through a remosaicing and demosaicing process, where moire artifacts will appear in the high frequency area.…”

Section: Cfamoire Datasetmentioning

confidence: 99%

NTIRE 2020 Challenge on Image Demoireing: Methods and Results

Yuan

Timofte²,

Leonardis³

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Self Cite

View full text Add to dashboard Cite

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. Demoireing is a difcult task of removing moire patterns from an image to reveal an underlying clean image. The challenge was divided into two tracks. Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image. Track 2 focused on the burst demoireing problem, where a set of degraded moire images of the same scene were provided as input, with the goal of producing a single demoired image as output. 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. The tracks had 142 and 99 registered participants, respectively, with a total of 14 and 6 submissions in the final testing stage. The entries span the current state-of-the-art in image and burst image demoireing problems.

show abstract

“…(a) Clean LR (top left, generated with bicubic downsampling) and its blurry or noisy versions with different k and n.The 2 nd row is with isotropic Gaussian kernels while the 3 rd row with anisotropic Gaussian, and σ is variance of additive Gaussian noise. The example image is from DIV8K[9]; (b) Image with typical patch recurrence, both within and across different scales of the same image. The image is from Urban100[10]; (c) Real-world smartphone images with complex unknown degradations.…”

mentioning

confidence: 99%

Blind Image Super-Resolution: A Survey and Beyond

Liu¹,

Liu²,

Gu³

et al. 2021

Preprint

View full text Add to dashboard Cite

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. Many novel and effective solutions have been proposed recently, especially with the powerful deep learning techniques. Despite years of efforts, it still remains as a challenging research problem. This paper serves as a systematic review on recent progress in blind image SR, and proposes a taxonomy to categorize existing methods into three different classes according to their ways of degradation modelling and the data used for solving the SR model. This taxonomy helps summarize and distinguish among existing methods. We hope to provide insights into current research states, as well as to reveal novel research directions worth exploring. In addition, we make a summary on commonly used datasets and previous competitions related to blind image SR. 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.

show abstract

DIV8K: DIVerse 8K Resolution Image Dataset

Cited by 64 publications

References 17 publications

FL-MISR: fast large-scale multi-image super-resolution for computed tomography based on multi-GPU acceleration

FL-MISR: fast large-scale multi-image super-resolution for computed tomography based on multi-GPU acceleration

NTIRE 2020 Challenge on Image Demoireing: Methods and Results

Blind Image Super-Resolution: A Survey and Beyond

Contact Info

Product

Resources

About