iccv iccv2013 iccv2013-408 iccv2013-408-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Carlos Fernandez-Granda, Emmanuel J. Candès
Abstract: We present a framework to super-resolve planar regions found in urban scenes and other man-made environments by taking into account their 3D geometry. Such regions have highly structured straight edges, but this prior is challenging to exploit due to deformations induced by the projection onto the imaging plane. Our method factors out such deformations by using recently developed tools based on convex optimization to learn a transform that maps the image to a domain where its gradient has a simple group-sparse structure. This allows to obtain a novel convex regularizer that enforces global consistency constraints between the edges of the image. Computational experiments with real images show that this data-driven approach to the design of regularizers promoting transform-invariant group sparsity is very effective at high super-resolution factors. We view our approach as complementary to most recent superresolution methods, which tend to focus on hallucinating high-frequency textures.
[1] S. Baker and T. Kanade. Limits on super-resolution and how to break them. Pattern Analysis and Machine Intelligence, IEEE Trans. on, 24(9): 1167–1 183, 2002. 1
[2] S. R. Becker, E. J. Cand e`s, and M. Grant. Templates for convex cone problems with applications to sparse signal recovery. Mathematical programming computation, 3(3): 165– 218, 2011. 4
[3] K. Bleakley and J.-P. Vert. The group fused lasso for multiple change-point detection. arXiv:1106.4199, 2011. 3
[4] E. J. Cand e`s and C. Fernandez-Granda. Towards a mathematical theory of super-resolution. Communications on Pure and Applied Mathematics. To appear. 1
[5] E. J. Cand e`s, X. Li, Y. Ma, and J. Wright. Robust principal component analysis? J. ACM, 58(3): 11:1–1 1:37, 2011. 4
[6] S. Farsiu, M. D. Robinson, M. Elad, and P. Milanfar. Fast and robust multiframe super resolution. Image processing, IEEE Trans. on, 13(10):1327–1344, 2004. 1
[7] G. Freedman and R. Fattal. Image and video upscaling from local self-examples. ACM Trans. on Graphics (TOG), 30(2): 12, 2011. 2
[8] W. T. Freeman, T. R. Jones, and E. C. Pasztor. Examplebased super-resolution. Computer Graphics and Applications, IEEE, 22(2):56–65, 2002. 2
[9] D. Glasner, S. Bagon, and M. Irani. Super-resolution from a single image. In ICCV, pages 349–356. IEEE, 2009. 2
[10] D. Krishnan and R. Fergus. Fast image deconvolution using hyper-laplacian priors. Advances in Neural Information Processing Systems, 22: 1–9, 2009. 2
[11] F. Malgouyres and F. Guichard. Edge direction preserving image zooming: a mathematical and numerical analysis. SIAM Journal on Numerical Analysis, 39(1): 1–37, 2001 . 2
[12] Q. Shan, Z. Li, J. Jia, and C.-K. Tang. Fast image/video upsampling. In ACM Trans. on Graphics (TOG), volume 27, page 153. ACM, 2008. 5
[13] J. Sun, J. Sun, Z. Xu, and H.-Y. Shum. Gradient profile prior and its applications in image super-resolution and enhancement. Image Processing, IEEE Trans. on, 20(6): 1529–1542, 2011. 2
[14] Y.-W. Tai, S. Liu, M. S. Brown, and S. Lin. Super resolution using edge prior and single image detail synthesis. In CVPR, pages 2400–2407, 2010. 2
[15] F. Viola, A. W. Fitzgibbon, and R. Cipolla. A unifying resolution-independent formulation for early vision. In CVPR, pages 494–501, 2012. 2
[16] J. Xiao, J. Hays, K. A. Ehinger, A. Oliva, and A. Torralba. Sun database: Large-scale scene recognition from abbey to zoo. In CVPR, pages 3485–3492, 2010. 5, 7
[17] J. Yang, J. Wright, T. S. Huang, and Y. Ma. Image superresolution via sparse representation. Image Processing, IEEE Trans. on, 19(1 1):2861–2873, 2010. 2, 5, 8
[18] M. Yuan and Y. Lin. Model selection and estimation in regression with grouped variables. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 68(1):49– 67, 2006. 2
[19] Z. Zhang, X. Liang, A. Ganesh, and Y. Ma. TILT: transform invariant low-rank textures. In Computer Vision–ACCV 2010, pages 3 14–328. Springer, 2011. 2, 3, 4 33333425 Input Bicubic (x8) TV (x8) Sparse Coding (x4) TI-DTV (x8) Figure 12. Results from super-resolving the images in Figure 8 using bicubic interpolation, total-variation regularization, sparse coding [17] and our proposed algorithm. The upsampling factor was 4 for sparse coding and 8 for the rest of the methods. the low-resolution images. 33333436