Learning Good Regions to Deblur Images

Springer Science and Business Media LLC - Tập 115 Số 3 - Trang 345-362 - 2015
Hu, Zhe1, Yang, Ming-Hsuan1
1School of Engineering, University of California at Merced, Merced, USA

Tóm tắt

The goal of single image deblurring is to recover both a latent clear image and an underlying blur kernel from one input blurred image. Recent methods focus on exploiting natural image priors or additional image observations for deblurring, but pay less attention to the influence of image structure on estimating blur kernels. What is the useful image structure and how can one select good regions for deblurring? We formulate the problem of learning good regions for deblurring within the conditional random field framework. To better compare blur kernels, we develop an effective similarity metric for labeling training samples. The learned model is able to predict good regions from an input blurred image for deblurring without user guidance. Qualitative and quantitative evaluations demonstrate that good regions can be selected by the proposed algorithms for effective single image deblurring.

Tài liệu tham khảo

Bae, H., Fowlkes, C. C., & Chou, P. H. (2012). Patch mosaic for fast motion deblurring. In Proceedings of Asian conference on computer vision (pp. 322–335). citation_journal_title=Optics Express; citation_title=A computational method for the restoration of images with an unknown, spatially-varying blur; citation_author=J Bardsley, S Jefferies, J Nagy, R Plemmons; citation_volume=14; citation_issue=5; citation_publication_date=2006; citation_pages=1767-1782; citation_doi=10.1364/OE.14.001767; citation_id=CR2 Ben-Ezra, M., & Nayar, S. (2003). Motion deblurring using hybrid imaging. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 657–664). citation_journal_title=Journal of the Royal Statistical Society: Series D; citation_title=Statistical analysis of non-lattice data; citation_author=J Besag; citation_volume=24; citation_issue=3; citation_publication_date=2006; citation_pages=179-195; citation_id=CR4 Cai, J., Ji, H., Liu, C., & Shen, Z. (2009). Blind motion deblurring from a single image using sparse approximation. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 104–111). Cho, S., & Lee, S. (2009). Fast motion deblurring. In Proceedings of ACM SIGGRAPH Asia. Cho., S., Matsushita, Y., & Lee, S. (2007). Removing non-uniform motion blur from images. In Proceedings of IEEE international conference on computer vision. Cho, T. S., Joshi, N., Zitnick, C. L., Kang, S. B., Szeliski, R., & Freeman, W. T. (2010). A content-aware image prior. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 169–176). Cho, T. S., Paris, S., Horn, B. K. P., & Freeman, W. T. (2011). Blur kernel estimation using the radon transform. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 241–248). Fergus, R., Singh, B., Hertzmann, A., Roweis, S. T., & Freeman, W. T. (2006). Removing camera shake from a single photograph. In Proceedings of ACM SIGGRAPH (pp. 787–794). citation_journal_title=The Computer Journal; citation_title=A new approach to variable metric algorithms; citation_author=R Fletcher; citation_volume=13; citation_issue=3; citation_publication_date=1970; citation_pages=317-322; citation_doi=10.1093/comjnl/13.3.317; citation_id=CR11 Goldstein, A., & Fattal, R. (2012). Blur-kernel estimation from spectral irregularities. In Proceedings of European conference on computer vision (pp. 622–635). Gupta, A., Joshi, N., Zitnick, L., Cohen, M., & Curless, B. (2010). Single image deblurring using motion density functions. In Proceedings of European conference on computer vision (pp. 171–184). Hirsch, M., Schuler, C.J., Harmeling, S., & Schölkopf, B. (2011). Fast removal of non-uniform camera shake. In Proceedings of IEEE international conference on computer vision (pp. 463–470). citation_journal_title=IEEE Transactions on Image Processing; citation_title=Psf estimation via gradient domain correlation; citation_author=W Hu, J Xue, N Zheng; citation_volume=21; citation_issue=1; citation_publication_date=2012; citation_pages=386-392; citation_doi=10.1109/TIP.2011.2160073; citation_id=CR15 Hu, Z., & Yang, M.H. (2012). Fast non-uniform deblurring using constrained camera pose subspace. In Proceedings of British machine vision conference. Hu, Z., & Yang, M. H. (2012). Good regions to deblur. In Proceedings of European conference on computer vision (pp. 59–72). Jia, J. (2007). Single image motion deblurring using transparency. In Proceedings of IEEE conference on computer vision and pattern recognition. Joshi, N., Kang, S. B., Zitnick, C. L., & Szeliski, R. (2010). Image deblurring using inertial measurement sensors. In Proceedings of ACM SIGGRAPH (p. 30). Joshi, N., Szeliski, R., & Kriegman, D. J. (2008). PSF estimation using sharp edge prediction. In Proceedings of IEEE conference on computer vision and pattern recognition. Köhler, R., Hirsch, M., Mohler, B., Schölkopf, B., & Harmeling, S. (2012). Recording and playback of camera shake: Benchmarking blind deconvolution with a real-world database. In Proceedings of European conference on computer vision (pp. 27–40). Krishnan, D., Tay, T., & Fergus, R. (2011). Blind deconvolution using a normalized sparsity measure. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 233–240). citation_journal_title=International Journal Computer Vision; citation_title=Discriminative random field; citation_author=S Kumar, M Hebert; citation_volume=68; citation_issue=2; citation_publication_date=2006; citation_pages=179-201; citation_doi=10.1007/s11263-006-7007-9; citation_id=CR23 Lafferty, J., McCallum, A., & Pereira, F. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of international conference on machine learning (pp. 282–289). Levin, A. (2006). Blind motion deblurring using image statistics. In Neural information processing systems (pp. 841–848). Levin, A., Weiss, Y., Durand, F., & Freeman, W. T. (2009). Understanding and evaluating blind deconvolution algorithms. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 1964–1971). Liu, S., Wang, H., Wang, J., Cho, S., & Pan, C. (2014). Automatic blur-kernel-size estimation for motion deblurring. The visual computer. Raskar, R., Agrawal, A., & Tumblin, J. (2006). Coded exposure photography: Motion deblurring using fluttered shutter. In Proceedings of ACM SIGGRAPH (pp. 795–804). Shan, Q., Jia, J., & Agarwala, A. (2008). High-quality motion deblurring from a single image. In Proceedings of ACM SIGGRAPH (pp. 73:1–73:10). Shan, Q., Xiong, W., & Jia, J. (2007). Rotational motion deblurring of a rigid object from a single image. In Proceedings of IEEE international conference on computer vision. citation_journal_title=IEEE Transactions on Pattern Analysis and Machine Intelligence; citation_title=Richardson-Lucy deblurring for scenes under projective motion path; citation_author=Y Tai, P Tan, MS Brown; citation_volume=33; citation_issue=8; citation_publication_date=2011; citation_pages=1603-1618; citation_doi=10.1109/TPAMI.2010.222; citation_id=CR31 Tai, Y. W., Du, H., Brown, M. S., & Lin, S. (2008). Image/video deblurring using a hybrid camera. In Proceedings of IEEE conference on computer vision and pattern recognition. Whyte, O., Sivic, J., Zisserman, A., & Ponce, J. (2010). Non-uniform deblurring for shaken images. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 491–498). Xu, L., & Jia, J. (2010). Two-phase kernel estimation for robust motion deblurring. In Proceedings of European conference on computer vision (pp. 157–170). Xu, L., Zheng, S., & Jia, J. (2013). Unnatural l0 sparse representation for natural image deblurring. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 1107–1114). Yedidia, J. S., Freeman, W. T., & Weiss, Y. (2003). Understanding belief propagation and its generalizations. In Exploring artificial intelligence in the new millennium (pp. 236–239). Morgan Kaufmann Publishers Inc. citation_journal_title=Journal of the Optical Society of America; citation_title=Direct method for restoration of motion-blurred images; citation_author=Y Yitzhaky, I Mor, A Lantzman, N Kopeika; citation_volume=15; citation_issue=6; citation_publication_date=1998; citation_pages=1512-1519; citation_doi=10.1364/JOSAA.15.001512; citation_id=CR37 citation_journal_title=Applied Mechanics and Materials; citation_title=Blur kernel optimization: A new approach to patch selection with adaptive kernel estimation; citation_author=S Yousaf, SY Qin; citation_volume=436; citation_publication_date=2013; citation_pages=531-538; citation_doi=10.4028/www.scientific.net/AMM.436.531; citation_id=CR38 Yuan, L., Sun, J., Quan, L., & Shum, H. (2007). Image deblurring with blurred/noisy image pairs. In Proceedings of ACM SIGGRAPH. Zhong, L., Cho, T. S., Metaxas, D., Paris, S., & Wang, J. (2013). Handling noise in single image deblurring using directional filters. In Proceedings of IEEE conference on computer vision and pattern recognition.