Abstract
Super-resolution (SR) is a technique that reconstructs high-resolution images using the information present in low-resolution images. Due to their potentials of being used in wide range of image and video applications, various SR algorithms have been studied and proposed in the literature until recently. However, many of the algorithms provide insufficient perceptual quality, possess high computational complexity, or have high memory requirement, which make them hard to apply on consumer-level products. Therefore, in this paper we propose an effective super-resolution method that not only provides an excellent visual quality but also a high-speed performance suitable for video conversion applications. The proposed super-resolution adopts self-similarity framework, which reconstructs the high-frequency (HF) information of the high-resolution image by referring to the image pairs generated from self-similar regions. The method further enhances the perceptual sharpness of the video through region-adaptive HF enhancement algorithm and applies iterative back projection to maintain its consistency with the input image. The proposed method is suitable for parallel processing and therefore is able to provide its superb visual quality on a high conversion speed through GPU-based acceleration. The experimental results show that the proposed method has superior HF reconstruction performance compared to other state-of-the-art upscaling solutions and is able to generate videos that are visually as sharp as the original high-resolution videos. On a single PC with four GPUs, the proposed method can convert Full HD resolution video into UHD resolution with real-time conversion speed. Due to its fast and high-quality conversion capability, the proposed method can be applied on various consumer products such as UHDTV, surveillance system, and mobile devices.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Hardie RC, Barnard KJ, Armstrong EA (1997) Joint MAP registration and high-resolution image estimation using a sequence of undersampled images. IEEE Trans Image Process 6:1621–1633
Farsiu S, Robinson MD, Elad M, Milanfar P (2004) Fast and robust multiframe super-resolution. IEEE Trans Image Process 13:1327–1344
Ng MK, Shen H, Lam EY, Zhang L (2007) A total variation regularization based super-resolution reconstruction algorithm for digital video. EURASIP J Adv Signal Process 2007:74585-1–74585-16
Yang J, Wang Z, Lin Z, Cohen S, Huang T (2012) Coupled dictionary training for image super-resolution. IEEE Trans Image Process 21(8):3467–3478
Peleg T, Elad M (2014) A statistical prediction model based on sparse representations for single image super-resolution. IEEE Trans Image Process 23(6):2569–2582
Zeyde R, Elad M, Protter M (2010) On single image scale-up using sparse-representations. In: Curves and surfaces, pp 711–730
Timofte R, De Smet V, Van Gool L (2014) A+: adjusted anchored neighborhood regression for fast super-resolution. In: Proceedings of Asian Conference on Computer Vision, Singapore
Dong C, Loy CC, He K, Tang X (2015) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38:295–307
Choi J-S, Kim M (2016) Super-interpolation with edge-orientation-based mapping kernels for low complex upscaling. IEEE Trans Image Process 25:469–483
Dong W, Zhang L, Shi G, Wu X (2011) Image deblurring and superresolution by adaptive sparse domain selection and adaptive regularization. IEEE Trans Image Process 20(7):1838–1857
Dong W, Zhang L, Shi G, Li X (2013) Nonlocally centralized sparse representation for image restoration. IEEE Trans Image Process 22(4):1620–1630
Kim J, Kwon Lee J, Mu Lee K (2016) Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Glasner D, Bagon S, Irani M (2009) Super-resolution from a single image. In: 12th International Conference on Computer Vision, pp 349–356
Freedman G, Fattal R (2011) Image and video upscaling from local self-examples. ACM Trans Graph 30, Article No. 12, April 2011
Yang J, Lin Z, Cohen S (2013) Fast image super-resolution based on in-place example regression. In: Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 23–28 June 2013, pp 1059–1066
Jun JH, Choi JH, Lee DY, Jeong S, Cho SH, Kim HY, Kim JO (2015) Accelerating self-similarity-based image super-resolution using OpenCL. IEIE Trans Smart Process Comput 4(1):10–15
Chen S, Gong H, Li C (2011) Super resolution from a single image based on self-similarity. In: IEEE International Conference on Computational and Information Sciences, Oct 2011, pp 91–94
Khronos OpenCL Working Group (2012) The OpenCL Specification Version 1.2. Khronos Group. http://www.khronos.org/opencl
Version 2.1.0, July 2016. http://www.infognition.com/videoenhancer/
Asuni N, Giachetti A (2008) Accuracy improvements and artifacts removal in edge based image interpolation. In: Proceedings Third International Conference Computer Vision Theory and Applications (VISAPP’08)
Giachetti A, Asuni N (2011) Real-time artifact-free image upscaling. IEEE Trans Image Process 20(10):2760–2768
Yang S, Kim Y, Jeong J (2008) Fine edge-preserving technique for display devices. IEEE Trans Consum Electron 54(4):1761–1769
Kang W et al (2013) Real-time super-resolution for digital zooming using finite kernel-based edge orientation estimation and truncated image restoration. In: Proceedings of 20th IEEE International Conference on Image Processing, Melbourne, VIC, Sept 2013, pp 1311–1315
Park SJ, Lee OY, Kim JO (2013) Self-similarity based image super-resolution on frequency domain. In: Proceedings of APSIPA ASC 2014, Nov 2013, pp 1–4
Wang Z, Bovik AC, Evans BI (2000) Blind measurement of blocking artifacts in images. In: IEEE International Conference on Image Processing, Sep 2000, pp 981–984
Bae S-H, Kim M (2014) A novel generalized DCT-based JND profile based on an elaborate CM-JND model for variable block-sized transforms in monochrome images. IEEE Trans Image Process 23(8):3227–3240
Alam MM (2014) Local masking in natural images: a database and analysis. J Vis 14(8):22–22
Ponomarenko N et al (2013) Color image database TID2013: peculiarities and preliminary results. In: Proceedings of 4th European Workshop on Visual Information Processing, June 2013, pp 106–111
Song L, Tang X, Zhang W, Yang X, Xia P (2013) The SJTU 4K video sequence dataset. In: The Fifth International Workshop on Quality of Multimedia Experience (QoMEX2013), Klagenfurt, 3rd–5th July 2013
Chen Q, Montesinos P, Sun Q, Heng P, Xia D (2010) Adaptive total variation denoising based on difference curvature. Image Comput 28(3):298–306
European Broadcast Union (2013) EBU UHD-1 Test Set (online). http://tech.ebu.ch/testsequences/uhd-1
Blender Foundation (2012) Tears of Steel, Mango Open Movie Project. http://tearsofsteel.org
Ulichney RA (1988) Dithering with blue noise. Proc IEEE 76(1):56–79
ITU-R BT.500-13 (2012) ITU, Methodology for the subjective assessment of the quality of television pictures
Acknowledgements
This work was supported by ICT R&D program of MSIP/IITP. [B0101-16-1280, Development of Cloud Computing Based Realistic Media Production Technology].
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lee, D.Y., Lee, J., Choi, JH. et al. GPU-based real-time super-resolution system for high-quality UHD video up-conversion. J Supercomput 74, 456–484 (2018). https://doi.org/10.1007/s11227-017-2136-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-017-2136-1