Learning Weighted Forest and Similar Structure for Image Super Resolution
Source abstract
Abstract
Image super resolution (SR) based on example learning is a very effective approach to achieve high resolution (HR) image from image input of low resolution (LR). The most popular method, however, depends on either the external training dataset or the internal similar structure, which limits the quality of image reconstruction. In the paper, we present a novel SR algorithm by learning weighted random forest and non-local similar structures. The initial HR image patches are obtained from a weighted forest model, which is established by calculating the approximate fitting error of the leaf nodes. The K-means clustering algorithm is exploited to get a non-local similar structure inside the initial HR image patches. In addition, a low rank constraint is imposed on the HR image patches in each cluster. We further apply the similar structure model to establish an effective regularization prior under a reconstruction-based SR framework. Comparing with current typical SR algorithms, the results of comprehensive experiments implemented on three publicly datasets show that peak signal-to-noise ratio (PSNR) has been effectively promoted by the presented SR approach, and a better visual effect has been realized.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Image Processing Techniques · Image and Signal Denoising Methods · Advanced Image Fusion Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Information Science and Engineering, Northeastern University, Shenyang 110819, China
School of Computer and Communication Engineering, Liaoning Shihua University, Fushun 113001, China
Faculty of Robot Science and Engineering, Northeastern University, Shenyang 110819, China
Funding
National Natural Science Foundation of China · National Key Robot Project
References (36)
Show source-provided references
1. Tsai, R.Y., and Huang, T.S. (1984). Multi-frame image restoration and registration. Advance in Computer Vision and Image Processing, JAI Press, Inc.
2. Cubic convolution interpolation for digital image processing10.1109/TASSP.1981.1163711 ↗
3. Kernel regression for image processing and reconstruction10.1109/TIP.2006.888330 ↗
4. New edge-directed interpolation10.1109/83.951537 ↗
5. An edge-guided image interpolation algorithm via directional filtering and data fusion10.1109/TIP.2006.877407 ↗
6. Markov random field model-based edge-directed image interpolation10.1109/TIP.2008.924289 ↗
7. Sun, J., Zhu, J., and Tappen, M.F. (2010, January 13–18). Context-constrained hallucination for image super-resolution. Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA.10.1109/CVPR.2010.5540206 ↗
8. Tai, Y., Tai, Y.W., Liu, S., Brown, M.S., and Lin, S. (2010, January 13–18). Super resolution using edge prior and single image detail synthesis. Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA.10.1109/CVPR.2010.5539933 ↗
9. Single image super-resolution with non-local means and steering kernel regression10.1109/TIP.2012.2208977 ↗
10. Single image super-resolution with detail enhancement based on local fractal analysis of gradient10.1109/TCSVT.2013.2248305 ↗
11. Edge-directed single-image super-resolution via adaptive gradient magnitude self-interpolation10.1109/TCSVT.2013.2240915 ↗
12. Example-based super-resolution10.1109/38.988747 ↗
13. Chang, N.H., Yeung, D.Y., and Xiong, N.Y. (July, January 27). Super-resolution through neighbor embedding. Proceedings of the 2004 IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, USA.
14. Yang, J.C., Wright, J., Huang, T., and Ma, Y. (2008, January 23–28). Image super-resolution as sparse representation of raw image patches. Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.
15. Image super-resolution via sparse representation10.1109/TIP.2010.2050625 ↗
16. Zeyde, R., Elad, M., and Protter, M. (2010, January 24–30). On single image scale-up using sparse-representations. Proceedings of the 7th International Conference on Curves and Surfaces, Avignon, France.
17. Timofte, R., De, V., and Gool, L.V. (2013, January 1–8). Anchored neighborhood regression for fast example-based super-resolution. Proceedings of the 2013 IEEE International Conference on Computer Vision, Sydney, Australia.10.1109/ICCV.2013.241 ↗
18. Timofte, R., Smet, V.D., and Gool, L.V. (2014, January 1–5). A+: Adjusted anchored neighborhood regression for fast super-resolution. Proceedings of the 12th Asian Conference on Computer Vision, Singapore.10.1109/ICCV.2013.241 ↗
19. Yang, C.Y., and Yang, M.H. (2013, January 1–8). Fast direct super-resolution by simple functions. Proceedings of the 2013 IEEE International Conference on Computer Vision, Sydney, Australia.10.1109/ICCV.2013.75 ↗
20. Jointly optimized regressors for image super-resolution10.1111/cgf.12544 ↗
21. Schulter, S., Leistner, C., and Bischof, H. (2015, January 7–12). Fast and accurate image upscaling with super resolution forest. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7299003 ↗
22. Dong, C., Loy, C.C., He, K.M., and Tang, X.O. (2014, January 6–12). Learning a deep convolutional network for image super-resolution. Proceedings of the 13th the European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10593-2_13 ↗
23. Zontak, M., and Irani, M. (2011, January 20–25). Internal statistics of a single natural image. Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.10.1109/CVPR.2011.5995401 ↗
24. Generalizing the nonlocal-means to super-resolution reconstruction10.1109/TIP.2008.2008067 ↗
25. Glasner, D., Bagon, S., and Irani, M. (October, January 29). Super-resolution from a single image. Proceedings of the IEEE 12th International Conference on Computer Vision, Kyoto, Japan.
26. Image and video upscaling from local self-examples10.1145/1944846.1944852 ↗
27. Michaeli, T., and Irani, M. (2013, January 1–8). Nonparametric blind super-resolution. Proceedings of the 2013 IEEE International Conference on Computer Vision, Sydney, Australia.10.1109/ICCV.2013.121 ↗
28. Single image super-resolution with multiscale similarity learning10.1109/TNNLS.2013.2262001 ↗
29. Huang, J.B., Singh, A., and Ahuja, N. (2015, January 7–12). Single image super-resolution from transformed self-exemplars. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7299156 ↗
30. Single image super-resolution via locally regularized anchored neighborhood regression and nonlocal means10.1109/TMM.2016.2599145 ↗
31. Single image super-resolution restoration algorithm from external example to internal self-similarity
32. Sparse Coding with an overcomplete basis set: A strategy employed by V1?10.1016/S0042-6989(97)00169-7 ↗
33. K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation10.1109/TSP.2006.881199 ↗
34. Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization10.1109/TIP.2011.2108306 ↗
35. Fast single image super-resolution using sparse Gaussian process regression10.1016/j.sigpro.2016.11.006 ↗
36. Learning local dictionaries and similarity structures for single image super-resolution10.1016/j.sigpro.2017.07.020 ↗