Single image super-resolution from transformed self-exemplars

Huang, Jia-Bin; Singh, Abhishek; Ahuja, Narendra

doi:10.1109/cvpr.2015.7299156

Cited by 2,757 publications

(1,476 citation statements)

References 30 publications

Supporting

Mentioning

1,470

Contrasting

Unclassified

Order By: Relevance

“…The experimental results illustrate the strengths and drawbacks of each method. According to the PSNR table and Time table we can conclude that, Method [24] produces the higher PSNR value over the other methods.…”

Section: Discussionmentioning

confidence: 99%

“…The super resolution output from method in [23] is shown in third row. Fourth row introduces the super resolution output from method in [24]. Finally, Fifth row represents the super resolution output from method in [17].…”

Section: Resultsmentioning

confidence: 99%

“…Figure. 1 Examples of recovering super resolution images. Row 1 represents the original images, row 2 represents the results of method [9], row 3 represents the results of method [23], row 4 represents the results of method [24], and row 5 represents the results of method [17].…”

Section: Resultsmentioning

confidence: 99%

“…The authors in [24] proposed an image super resolution method based on transformed selfexemplars. The algorithm produces the high resolution image by using the following steps: 1) Compute a transformation matrix T (homography) that warps target patch P to its best matching patch Q (source patch) in the down sampled image ID for each patch P in the low resolution image I.…”

Section: Super-resolution From Transformed Self-exemplarsmentioning

confidence: 99%

See 3 more Smart Citations

Single Image Super Resolution : A Comparative Study

Youssef¹,

Zarif²,

Ghoneim³

2017

Computer Science &Amp; Information Technology (CS &Amp; IT)

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Super-resolution From Transformed Self-exemplarsmentioning

confidence: 99%

See 2 more Smart Citations

Single Image Super Resolution : A Comparative Study

Youssef¹,

Zarif²,

Ghoneim³

2017

Computer Science &Amp; Information Technology (CS &Amp; IT)

View full text Add to dashboard Cite

show abstract

“…This is performed with SR, which is a technique mapping a low resolution image and a high resolution image. Image processing researchers have been proposed various SR techniques including singular vector decomposition [15], single image super-resolution [16], and convolutional neural network (SRCNN) [10]. For this research, Dong et al [10]'s work using SRCNN is applied and their open-source code was utilized.…”

Section: Super-resolution For High Resolution Ultrasonic Image Recovementioning

confidence: 99%

Reconstruction of laser ultrasonic wavefield images from reduced sparse measurements using compressed sensing aided super-resolution

Park¹,

Sohn²

2017

AIP Conference Proceedings

View full text Add to dashboard Cite

Abstract. Laser ultrasonic scanning is attractive for damage detection due to its noncontact nature, sensitivity to local damage, and high spatial resolution. However, its practicality is limited because scanning at a high spatial resolution demands a prohibitively long scanning time. Recently, compressed sensing (CS) and super-resolution (SR) are gaining popularity in the image recovery field. CS estimates unmeasured ultrasonic responses from measured responses, and SR recovers high spatial frequency information from low resolution images. Inspired by these techniques, a laser ultrasonic wavefield reconstruction technique is developed to localize and visualize damage with a reduced number of ultrasonic measurements. First, a low spatial resolution ultrasonic wavefield image for a given inspection region is reconstructed from reduced number of ultrasonic measurements using CS. Here, the ultrasonic waves are generated using a pulsed laser, and measured at a fixed sensing point using a laser Doppler vibrometer (LDV). Then, a high spatial resolution ultrasonic wave image is recovered from the reconstructed low spatial resolution image using SR. The number of measurement points required for ultrasonic wavefield imaging is significantly reduced over 90%. The performance of the proposed technique is validated by an experiment performed on a cracked aluminum plate.

show abstract