Hybrid Example-Based Single Image Super-Resolution

Xian, Yang; Yang, Xiaodong; Tian, Yingli

doi:10.1007/978-3-319-27863-6_1

Cited by 5 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The quality is evaluated with competing approaches in terms of PSNR, SSIM. The method was compared to our recent LFHYSR approach [2], bicubic interpolation, Wanner and Goldluecke [14], MISR [12] and HYSISR [13]. For visual comparison results, see Figure 3.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Disparity-Assisted Block Matching-Based Approach for Super-Resolution of Light Field Images

Farag

Velisavljević

2018

2018 - 3dtv-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3dtv-Con)

View full text Add to dashboard Cite

Currently, available plenoptic imaging technology has limited resolution. That makes it challenging to use this technology in applications, where sharpness is essential, such as film industry. Previous attempts aimed at enhancing the spatial resolution of plenoptic light field (LF) images were based on block and patch matching inherited from classical image super-resolution, where multiple views were considered as separate frames. By contrast to these approaches, a novel super-resolution technique is proposed in this paper with a focus on exploiting estimated disparity information to reduce the matching area in the super-resolution process. We estimate the disparity information from the interpolated LR view point images (VPs). We denote our method as light field block matching super-resolution. We additionally combine our novel super-resolution method with directionally adaptive image interpolation from [1] to preserve sharpness of the high-resolution images. We prove a steady gain in the PSNR and SSIM quality of the super-resolved images for the resolution enhancement factor 8x8 as compared to the recent approaches and also to our previous work [2].

show abstract

Section: Resultsmentioning

confidence: 99%

“…Finally, we demonstrate the robustness of the proposed novel technique for solving LF processing tasks, namely the LFSR. As compared to the current LFSR images, the proposed novel approach efficiently produces far better quality images as opposed to the images obtained with the use of the MISR [12], and HYSISR [13].…”

Section: Introductionmentioning

confidence: 99%

A Novel Disparity-Assisted Block Matching-Based Approach for Super-Resolution of Light Field Images

Farag

Velisavljević

2018

2018 - 3dtv-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3dtv-Con)

View full text Add to dashboard Cite

show abstract

“…Learning-based super-resolution (SR) is a post-processing technique to increase image resolution [2][3][4]. Wu et al developed a learning-based super resolution technique using kernel partial least squares [2].…”

Section: Introductionmentioning

confidence: 99%

“…Wu et al developed a learning-based super resolution technique using kernel partial least squares [2]. Xian et al also proposed an SR approach that integrates external and internal statistics [3]. Although these studies demonstrate that learning-based SR techniques can achieve high performance, these techniques require a large number of reference images and also take an enormous amount of time to compute.…”

Section: Introductionmentioning

confidence: 99%

Improving Image Resolution of Whole-Heart Coronary MRA Using Convolutional Neural Network

et al. 2019

View full text Add to dashboard Cite

Whole-heart coronary magnetic resonance angiography (WHCMRA) permits the noninvasive assessment of coronary artery disease without radiation exposure. However, the image resolution of WHCMRA is limited. Recently, convolutional neural networks (CNNs) have obtained increased interest as a method for improving the resolution of medical images. The purpose of this study is to improve the resolution of WHCMRA images using a CNN. Free-breathing WHCMRA images with 512 × 512 pixels (pixel size = 0.65 mm) were acquired in 80 patients with known or suspected coronary artery disease using a 1.5 T magnetic resonance (MR) system with 32 channel coils. A CNN model was optimized by evaluating CNNs with different structures. The proposed CNN model was trained based on the relationship of signal patterns between low-resolution patches (small regions) and the corresponding high-resolution patches using a training dataset collected from 40 patients. Images with 512 × 512 pixels were restored from 256 × 256 down-sampled WHCMRA images (pixel size = 1.3 mm) with three different approaches: the proposed CNN, bicubic interpolation (BCI), and the previously reported super-resolution CNN (SRCNN). Highresolution WHCMRA images obtained using the proposed CNN model were significantly better than those of BCI and SRCNN in terms of root mean squared error, peak signal to noise ratio, and structure similarity index measure with respect to the original WHCMRA images. The proposed CNN approach can provide high-resolution WHCMRA images with better accuracy than BCI and SRCNN. The high-resolution WHCMRA obtained using the proposed CNN model will be useful for identifying coronary artery disease.

show abstract

Towards breaking the spatial resolution barriers: An optical flow and super-resolution approach for sea ice motion estimation

Petrou

Xian

2018

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

Hybrid Example-Based Single Image Super-Resolution

Cited by 5 publications

References 25 publications

A Novel Disparity-Assisted Block Matching-Based Approach for Super-Resolution of Light Field Images

A Novel Disparity-Assisted Block Matching-Based Approach for Super-Resolution of Light Field Images

Improving Image Resolution of Whole-Heart Coronary MRA Using Convolutional Neural Network

Towards breaking the spatial resolution barriers: An optical flow and super-resolution approach for sea ice motion estimation

Contact Info

Product

Resources

About