Abstract
Remarkable up-scaling results are obtained from local self-examples (LSE) [1] at low cost. However, fine-detailed and cluttered regions are not reproduced realistically due to inappropriate addition of high frequency, and thus appear somewhat faceted and slightly distorted at edges. In this paper, an optimized algorithm that reduces these artifacts is proposed. A selective search is applied in the original restricted searching area. Mismatches can be avoided when patches are with extremely random details. Meanwhile we extend the local self-similarity on natural images to sub-pixel level which makes the assumption of local self-similarity more suitable especially for fine edge areas. It corrects the slightly misalignments when scaled with small factor. The proposed algorithm remains simple, and generates clear and believable textures compared with the original LSE and other mainstream methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Freedman, G., Fattal, R.: Image and video upscaling from local self-examples. ACM Trans. Graph. (2011)
Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: IEEE Conference on Computer Vision (2009)
Han, J.-W., et al.: A novel image interpolation method using the bilateral filter. IEEE Trans. Consum. Electron. (2010)
Yang, C.-Y., Huang, J.-B., Yang, M.-H.: Exploiting self-similarities for single frame super-resolution. In: Asian Conference on Computer Vision (2011)
Freeman, W.T., Jones, T.R., Pasztor, E.C.: Example-based super-resolution. Comput. Graph. Appl. 22, 56–65 (2002)
Park, S.C., Park, M.K., Kang, M.G.: Super-resolution image reconstruction: a technical overview. Sign. Process. Mag. 20, 21–36 (2003)
Li, X., Orchard, M.T.: New edge-directed interpolation. IEEE Trans. Image Process. 10, 1521–1527 (2001)
Giachetti, A., Asuni, N.: Real-time artifact-free image upscaling. IEEE Trans. Image Process. 20, 2760–2768 (2011)
Shan, Q., et al.: Fast image and video up-sampling. ACM Trans. Graph. (2008)
Fattal, R.: Image upsampling via imposed edge statistics. ACM Trans. Graph. (2007)
Kwatra, V., et al.: Texture optimization for example-based synthesis. ACM Trans. Graph. 24, 795–802 (2005)
Chang, H., Yeung, D.-Y., Xiong, Y.: Super-resolution through neighbor embedding. In: IEEE Conference on Computer Vision and Pattern Recognition (2004)
Lin, Z., Shum, H.-Y.: Fundamental limits of reconstruction-based super resolution algorithms under local translation. IEEE Trans. Pattern Anal. Mach. Intell. 26, 83–97 (2004)
Yang, J., et al.: Image super-resolution as sparse representation of raw image patches. In: IEEE Conference on Computer Vision and Pattern Recognition (2008)
JCTVC: High Efficiency Video Coding (HEVC) Test Model 10 Encoder Description. In JCTVC-L1002_v3 (2013)
Acknowledgements
This research is partly supported by NSFC, China (No: 61572315, 6151101179) and 863 Plan, China (No. 2015AA042308).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Jiang, H., Yang, J. (2017). Optimized Image Up-Scaling from Learning Selective Similarity. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10636. Springer, Cham. https://doi.org/10.1007/978-3-319-70090-8_48
Download citation
DOI: https://doi.org/10.1007/978-3-319-70090-8_48
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70089-2
Online ISBN: 978-3-319-70090-8
eBook Packages: Computer ScienceComputer Science (R0)