ABSTRACT
Cutting out objects from an image and estimating the corresponding transparency masks is a key step in post-production. One popular technique for pulling the transparency values is the closed-form approach of Levin et al.[6]. It is used in many matting algorithms for smoothing the initial noisy guess of the transparency map. Recently we proposed in [8] a more efficient alternative formulation to the original closed-form approach. In the new formulation the matting model parameters are fully exposed, which allows for more useful spatial constraints to be defined. We present in this paper how this new approach [8] can be sped up by considering local re-parametrisation of the matting model.
- X. Chen, D. Zou, S. Zhou, Q. Zhao, and P. Tan. Image matting with local and nonlocal smooth priors. In Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pages 1902--1907, June 2013. Google ScholarDigital Library
- Y.-Y. Chuang, B. Curless, D. Salesin, and R. Szeliski. A bayesian approach to digital matting. In Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on, volume 2, pages II--264--II--271 vol.2, 2001.Google Scholar
- K. He, C. Rhemann, C. Rother, X. Tang, and J. Sun. A global sampling method for alpha matting. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages 2049--2056, June 2011. Google ScholarDigital Library
- P. M. Hillman and J. M. Hannah. Natural Image Matting. In International Conference on Video, Vision and Graphics, pages 211--218, 2005.Google Scholar
- L. Karacan, A. Erdem, and E. Erdem. Image matting with kl-divergence based sparse sampling. June 2015.Google ScholarDigital Library
- A. Levin, D. Lischinski, and Y. Weiss. A closed-form solution to natural image matting. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 30(2):228--242, Feb 2008. Google ScholarDigital Library
- F. Pitié. Alternative Matting Laplacian reference code. https://github.com/frcs/alternative-matting-laplacian.Google Scholar
- F. Pitié. Alternative Matting Laplacian. In International Conference on Image Processing (ICIP). IEEE, 2016. https://arxiv.org/abs/1605.04785.Google Scholar
- C. Rhemann, C. Rother, J. Wang, M. Gelautz, P. Kohli, and P. Rott. Alpha matting evaluation website. http://www.alphamatting.com.Google Scholar
- C. Rhemann, C. Rother, J. Wang, M. Gelautz, P. Kohli, and P. Rott. A perceptually motivated online benchmark for image matting. In Proceddings of the IEEE Conference on Computer Vision and Pattern Recognition, 2009. Posterpräsentation: IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR '09, Miami, Florida, USA; 2009-06-20 -- 2009-06-25.Google ScholarCross Ref
- E. Shahrian, D. Rajan, B. Price, and S. Cohen. Improving image matting using comprehensive sampling sets. In Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pages 636--643, June 2013. Google ScholarDigital Library
- D. Singaraju, C. Rother, and C. Rhemann. New appearance models for natural image matting. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pages 659--666, June 2009.Google ScholarCross Ref
Index Terms
- Rank Reduced Alternative Matting Laplacian
Recommendations
A Bayesian Approach to Clustering Matting Components in Spectral Matting
ICIG '13: Proceedings of the 2013 Seventh International Conference on Image and GraphicsThis paper proposes to apply Bayesian principle to clustering matting components in spectral matting. Spectral matting is a useful and effective technique for digital image matting. A crucial issue of spectral matting is how to cluster the computed ...
Background subtraction driven seeds selection for moving objects segmentation and matting
In this paper, we address the difficult task of moving objects segmentation and matting in dynamic scenes. Toward this end, we propose a new automatic way to integrate a background subtraction (BGS) and an alpha matting technique via a heuristic seeds ...
Adaptive propagation matting based on transparency of image
Image matting is an essential technique in many image and video editing applications. Although many matting methods have been proposed, it is still a challenge for most to obtain satisfactory matting results in the transparent foreground region of an ...
Comments