Non-convex Relaxation of Optimal Transport for Color Transfer Between Images

详细信息    查看全文

• 关键词：Optimal transport ; Relaxation ; Color transfer
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：9389
• 期：1
• 页码：87-95
• 全文大小：1,905 KB
• 参考文献：1.Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE TPAMI 34(11), 2274–2282 (2012)CrossRef
  2.Attouch, H., Bolte, J., Svaiter, B.: Convergence of descent methods for semi-algebraic and tame problems. Math. Program. 137(1–2), 91–129 (2013)MathSciNet CrossRef MATH
  3.Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: NIPS 2013, pp. 2292–2300 (2013)
  4.Ferradans, S., Papadakis, N., Peyré, G., Aujol, J.F.: Regularized discrete optimal transport. SIAM J. Imaging Sci. 7(3), 1853–1882 (2014)MathSciNet CrossRef MATH
  5. Ferradans, S., Papadakis, N., Rabin, J., Peyré, G., Aujol, J.F.: Blind deblurring using a simplified sharpness index. In: Kuijper, A., Bredies, K., Pock, T., Bischof, H. (eds.) SSVM 2013. LNCS, vol. 7893, pp. 86–97. Springer, Heidelberg (2013) CrossRef
  6.Morovic, J., Sun, P.L.: Accurate 3d image colour histogram transformation. Pattern Recogn. Lett. 24(11), 1725–1735 (2003)CrossRef
  7.Nikolova, M., Wen, Y.W., Chan, R.H.: Exact histogram specification for digital images using a variational approach. JMIV 46(3), 309–325 (2013)MathSciNet CrossRef MATH
  8.Ochs, P., Chen, Y., Brox, T., Pock, T.: ipiano: inertial proximal algorithm for nonconvex optimization. SIAM J. Imaging Sci. 7(2), 1388–1419 (2014)MathSciNet CrossRef MATH
  9.Papadakis, N., Bugeau, A., Caselles, V.: Image editing with spatiograms transfer. IEEE TIP 21(5), 2513–2522 (2012)MathSciNet
  10.Papadakis, N., Provenzi, E., Caselles, V.: A variational model for histogram transfer of color images. IEEE TIP 20(6), 1682–1695 (2011)MathSciNet
  11.Pitié, F., Kokaram, A.C., Dahyot, R.: Automated colour grading using colour distribution transfer. CVIU 107, 123–137 (2007)
  12.Pouli, T., Reinhard, E.: Progressive color transfer for images of arbitrary dynamic range. Comput. Graph. 35(1), 67–80 (2011)CrossRef
  13.Rabin, J., Delon, J., Gousseau, Y.: Removing artefacts from color and contrast modifications. IEEE TIP 20(11), 3073–3085 (2011)MathSciNet
  14.Rabin, J., Peyré, G.: Wasserstein regularization of imaging problem. In: IEEE ICIP 2011, pp. 1541–1544 (2011)
  15. Rabin, J., Peyré, G., Delon, J., Bernot, M.: Wasserstein barycenter and its application to texture mixing. In: Bruckstein, A.M., ter Haar Romeny, B.M., Bronstein, A.M., Bronstein, M.M. (eds.) SSVM 2011. LNCS, vol. 6667, pp. 435–446. Springer, Heidelberg (2012) CrossRef
  16.Rabin, J., Ferradans, S., Papadakis, N.: Adaptive color transfer with relaxed optimal transport. In: IEEE ICIP 2014 (2014)
  17.Reinhard, E., Adhikhmin, M., Gooch, B., Shirley, P.: Color transfer between images. IEEE Trans. Comput. Graphics Appl. 21(5), 34–41 (2001)CrossRef
  18.Su, Z., Zeng, K., Liu, L., Li, B., Luo, X.: Corruptive artifacts suppression for example-based color transfer. IEEE Trans. Multimedia 16(4), 988–999 (2014)CrossRef
  19.Tai, Y.W., Jia, J., Tang, C.K.: Local color transfer via probabilistic segmentation by expectation-maximization. In: CVPR 2005, pp. 747–754 (2005)
  20.Xiao, X., Ma, L.: Color transfer in correlated color space. In: ACM VRCIA 2006, pp. 305–309 (2006)
  
• 作者单位：Julien Rabin (15)
  Nicolas Papadakis (16)
  
  15. GREYC, UMR 6072, Université de Caen, 14050, Caen, France
  16. CNRS, IMB, UMR 5251, 33400, Talence, France
  
• 丛书名：Geometric Science of Information
• ISBN：978-3-319-25040-3
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

Optimal transport (OT) is a major statistical tool to measure similarity between features or to match and average features. However, OT requires some relaxation and regularization to be robust to outliers. With relaxed methods, as one feature can be matched to several ones, important interpolations between different features arise. This is not an issue for comparison purposes, but it involves strong and unwanted smoothing for transfer applications. We thus introduce a new regularized method based on a non-convex formulation that minimizes transport dispersion by enforcing the one-to-one matching of features. The interest of the approach is demonstrated for color transfer purposes.