Efficient FPGA implementation of a high-quality super-resolution algorithm with real-time performance

Szydzik, Tomasz; Callicó, Gustavo M.; Núñez, Antonio

doi:10.1109/tce.2011.5955206

Cited by 22 publications

(13 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The proposed 11-pipeline implementation on xc6vlx240t consumes a similar number of LUTs with that of the 4-core UHDTV case of [20] to achieve one order of magnitude faster execution than [20] running on Altera Aria II FPGA. Finally, when comparing to more demanding motion-estimation based SR implementations, the proposed FPGA design proves to be significantly faster and considerably cheaper: for QCIF image upsampling, a single-pipeline on Virtex5 provides up to 400x more fps with around 3x less LUTs than [49] (note however that, in general, motion-estimation based SR provides higher quality results).…”

Section: Design Exploration and Implementation Resultsmentioning

confidence: 99%

Acceleration techniques and evaluation on multi-core CPU, GPU and FPGA for image processing and super-resolution

Georgis

Lentaris

Reisis

2016

J Real-Time Image Proc

View full text Add to dashboard Cite

Super-Resolution (SR) techniques constitute a key element in image applications, which need highresolution reconstruction while in the worst case only a single low-resolution observation is available. SR techniques involve computationally demanding processes and thus researchers are currently focusing on SR performance acceleration. Aiming at improving the SR performance, the current paper builds up on the characteristics of the L-SEABI Super-Resolution (SR) method to introduce parallelization techniques for GPUs and FPGAs. The proposed techniques accelerate GPU reconstruction of Ultra-High Definition content, by achieving three (3x) times faster than the real-time performance on mid-range and previous generation devices and at least nine times (9x) faster than the real-time performance on high-end GPUs. The FPGA design leads to a scalable architecture performing four (4x) times faster than the real-time on low-end Xilinx Virtex 5 devices and sixty-nine times (69x) faster than the real-time on the Virtex 2000t. Moreover, we confirm the benefits of the proposed acceleration techniques by employing them on a different category of image-processing algorithms: on window-based Disparity functions, for which the proposed GPU technique shows an improvement over the CPU performance ranging from 14 times (14x) to 64 times (64x) while the proposed FPGA architecture provides 29x acceleration.

show abstract

Section: Design Exploration and Implementation Resultsmentioning

confidence: 99%

Acceleration techniques and evaluation on multi-core CPU, GPU and FPGA for image processing and super-resolution

Georgis

Lentaris

Reisis

2016

J Real-Time Image Proc

View full text Add to dashboard Cite

show abstract

“…For fusing the scaled LR images, different filters can be used, such as mean and median filters [125], [156], [157], [190], [216], [299], [479], adaptive normalized averaging [167], Adaboost classifier [364], and SVD-based filters [582]. These algorithms have been shown to be much faster than the IBP algorithms [ [58], [74], [115], [116], [124], [125], [156], [157], [226] (the last five are known as shift and add), [167], [176], [190], [299], [319], [364], [397], [479], [544], [546], [582] Non-parametric [418], [419], [426], [439], [514], [560], [563], [617] In [125], [156], [157], [216] it was shown that the median fusion of the LR images when they are registered, is equivalent to the ML estimation of the residual of the imaging model of Eq. (4) and results in a robust SR algorithm if the motion be...…”

Section: Direct Methodsmentioning

confidence: 99%

“…Beside increasing the speed of the algorithm it has been shown that this increases the robustness of the algorithm against the outliers which can be generated by different sources of errors, such as errors in the motion estimation [124]. Table 5 Reported IBP works [5], [6], [8], [13], [14] [124], [125], [128], [138], [147], [172], [177], [242], [249], [264], [270], [279], [280] [284], [325], [369], [392], [406], [446], [492], [501], [539], [546], [552] …”

Section: Iterative Back Projectionmentioning

confidence: 99%

Super-resolution: a comprehensive survey

Nasrollahi

Moeslund

2014

Machine Vision and Applications

589

292

View full text Add to dashboard Cite

Super-resolution, the process of obtaining one or more high-resolution images from one or more low-resolution observations, has been a very attractive research topic over the last two decades. It has found practical applications in many real world problems in different fields, from satellite and aerial imaging to medical image processing, to facial image analysis, text image analysis, sign and number plates reading, and biometrics recognition, to name a few. This has resulted in many research papers, each developing a new superresolution algorithm for a specific purpose. The current comprehensive survey provides an overview of most of these published works by grouping them in a broad taxonomy. For each of the groups in the taxonomy, the basic concepts of the algorithms are first explained and then the paths through which each of these groups have evolved are given in detail, by mentioning the contributions of different authors to the basic concepts of each group. Furthermore, common issues in super-resolution algorithms, such as imaging models and registration algorithms, optimization of the cost functions employed, dealing with color information, improvement factors, assessment of super-resolution algorithms, and the most commonly employed databases are discussed.

show abstract

“…A wide variety of such methods have been proposed in the literature [2][3][4][5][6]. Most of these methods begin with registration of LR frames to a common HR reference grid.…”

Section: Introductionmentioning

confidence: 99%

A collaborative adaptive Wiener filter for multi-frame super-resolution

Mohamed

Hardie

2015

Front. Phys.

View full text Add to dashboard Cite

Factors that can limit the effective resolution of an imaging system may include aliasing from under-sampling, blur from the optics and external factors, and sensor noise. Image restoration and super-resolution (SR) techniques can be used to improve image resolution. One SR method, developed recently, is the adaptive Wiener filter (AWF) SR algorithm. This is a multi-frame SR method that combines registered temporal frames through a joint nonuniform interpolation and restoration process to provide a high-resolution image estimate. Variations of this method have been demonstrated to be effective for multi-frame SR, as well demosaicing RGB and polarimetric imagery. While the AWF SR method effectively exploits subpixel shifts between temporal frames, it does not exploit self similarity within the observed imagery. However, very recently, the current authors have developed a multi-patch extension of the AWF method. This new method is referred to as a collaborative AWF (CAWF). The CAWF method employs a finite size moving window. At each position, we identify the most similar patches in the image within a given search window about the reference patch. A single-stage weighted sum of all of the pixels in all of the similar patches is used to estimate the center pixel in the reference patch. Like the AWF, the CAWF can perform nonuniform interpolation, deblurring, and denoising jointly. The big advantage of the CAWF, vs. the AWF, is the CAWF can also exploit self-similarity. This is particularly beneficial for treating low signal-to-noise ratio (SNR) imagery. To date, the CAWF has only been developed for Nyquist-sampled single-frame image restoration. In this paper, we extend the CAWF method for multi-frame SR. We provide a quantitative performance comparison between the CAWF SR and the AWF SR techniques using real and simulated data. We demonstrate that CAWF SR outperforms AWF SR, especially in low SNR applications.

show abstract

Efficient FPGA implementation of a high-quality super-resolution algorithm with real-time performance

Cited by 22 publications

References 10 publications

Acceleration techniques and evaluation on multi-core CPU, GPU and FPGA for image processing and super-resolution

Acceleration techniques and evaluation on multi-core CPU, GPU and FPGA for image processing and super-resolution

Super-resolution: a comprehensive survey

A collaborative adaptive Wiener filter for multi-frame super-resolution

Contact Info

Product

Resources

About