Abstract
Edge-directed single image super-resolution methods have been paid more attentions due to their sharp edge preserving in the recovered high-resolution image. Their core is the high-resolution gradient estimation. In this paper, we propose a novel cross-resolution gradient sharpening function learning to obtain the high-resolution gradient. The main idea of cross-resolution learning is to learn a sharpening function from low-resolution, and use it in high-resolution. Specifically, a blurred low-resolution image is first constructed by performing bicubic down-sampling and up-sampling operations sequentially. The gradient sharpening function considered as a linear transform is learned from blurred low-resolution gradient to the input low-resolution image gradient. After that, the high-resolution gradient is estimated by applying the learned gradient sharpening function to the initial blurred gradient obtained from the bicubic up-sampled of the low-resolution image. Finally, edge-directed single image super-resolution reconstruction is performed to obtain the sharpened high-resolution image. Extensive experiments demonstrate the effectiveness of our method in comparison with the state-of-the-art approaches.
Similar content being viewed by others
Notes
Note that, the interpolation based methods can also be regarded as single image super-resolution method. However, they are not very related to our work. Thereby, we do not review them in detail in this paper.
References
Baker S, Kanade T (2002) Limits on super-resolution and how to break them. IEEE Trans Pattern Anal Mach Intell 24(9):1167–1183
Chang H, Yeung D-Y, Xiong Y (2004) Super-resolution through neighbor embedding. In: Proceedings IEEE conference computer vision pattern recognition, pp 275–282
Dai S, Han M, Xu W, Wu Y, Gong Y (2007) Soft edge smoothness prior for alpha channel super resolution. In: Proceedings IEEE conference computer vision pattern recognition, pp 1–8
Fattal R (2007) Image upsampling via imposed edge statistics. ACM Trans Graph 26(13):95:1–95:5
Fattal R (2007) Image upsampling via imposed edge statistics. ACM Trans Graph (Proceedings of SIGGRAPH 2007) 26(13):95:1–95:8
Freedman G, Fattal R (2010) Image and video upscaling from local self-examples. ACM Trans Graph 28(3):1–10
Freeman WT, Jones TR, Pasztor EC (2002) Example-based superresolution. IEEE Comput Graph Appl 22(2):56–65
Glasner D, Bagon S, Irani M (2009) Super-resolution from a single image. In: International conference on computer vision, pp 349–356
Irani M, Peleg S (1993) Motion analysis for image enhancement: Resolution, occlusion and transparency. J Vis Commun Image Represent 4(4):324–335
Kim K, Kwon Y (2008) Example-based learning for singleimage SR and JPEG artifact removal, Max Planck’Insitut fur biologische Kybernetik, Tbingen, Germany Tech, Rep
Lin Z, Shum H-Y (2004) Fundamental limits of reconstruction-based superresolution algorithms under local translation. IEEE Trans Pattern Anal Mach Intell 26(1):83–97
Morse BS, Schwartzwald D (2001) Image magnification using level set reconstruction. In: Proceedings IEEE conference computer vision pattern recognition, pp 333–340
Shan Q, Li Z, Jia J, Tang C-K (2008) Fast image/video upsampling. ACM Transactions on Graphics (SIGGRAPH ASIA) 127(17):153:1–153:7
Sun J, Xu Z, Shum H-Y (2008) Image super-resolution using gradient profile prior. In: Proceedings IEEE conference computer vision pattern recognition, pp 1–8
Sun J, Xu Z, Shum H-Y (2011) Gradient profile prior and its applications in image super-resolution and enhancement. IEEE Trans Image Process 20(6):1529–1542
Tai Y-W, Liu S, Brown MS, Lin S (2010) Super resolution using edge prior and single image detail synthesis. In: Proceedings IEEE conference computer vision pattern recognition, pp 2400–2407
Wang LF, Xiang SM, Meng GF, Wu HY, Pan CH (2013) Edge-Directed Single-Image Super-Resolution Via Adaptive Gradient Magnitude Self-Interpolation. IEEE Trans Circuits Syst Video Technol 23(8):1289–1299
Yang J, Lin Z, Cohen S (2013) Fast image super-resolution based on in-place example regression. In: IEEE conference on computer vision and pattern recognition, pp 1059–1066
Yang J, Wright J, Ma Y, Huang T (2008) Image super-resolution as sparse representation of raw image patches. In: Proceedings IEEE conference computer vision pattern recognition, pp 1–8
Yang J, Wright J, Huang TS, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported in part by the National Natural Science Foundation of China (Grant Nos. 61263046, 61403376 and 61175025).
Rights and permissions
About this article
Cite this article
Han, W., Chu, J., Wang, L. et al. Edge-directed single image super-resolution via cross-resolution sharpening function learning. Multimed Tools Appl 76, 11143–11155 (2017). https://doi.org/10.1007/s11042-016-3656-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-3656-z