A Novel Edit Propagation Algorithm via \( L_0 \) Gradient Minimization

详细信息    查看全文

• 关键词：Edit propagation ; \(L_0 \) ; gradient minimization ; Recoloring ; Tonal adjustment
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：9314
• 期：1
• 页码：402-410
• 全文大小：471 KB
• 参考文献：1.An, X., Pellacini, F.: Appprop: all-pairs appearance-space edit propagation. ACM Trans. Graph. (TOG) 27, 40 (2008)
  2.Farbman, Z., Fattal, R., Lischinski, D.: Diffusion maps for edge-aware image editing. ACM Trans. Graph. (TOG) 29, 145 (2010)CrossRef
  3.Farbman, Z., Fattal, R., Lischinski, D., Szeliski, R.: Edge-preserving decompositions for multi-scale tone and detail manipulation. ACM Trans. Graph. (TOG) 27, 67 (2008)CrossRef
  4.Gastal, E.S., Oliveira, M.M.: Adaptive manifolds for real-time high-dimensional filtering. ACM Trans. Graph. (TOG) 31(4), 33 (2012)CrossRef
  5. He, K., Sun, J., Tang, X.: Guided image filtering. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 1–14. Springer, Heidelberg (2010) CrossRef
  6.Kopf, J., Cohen, M.F., Lischinski, D., Uyttendaele, M.: Joint bilateral upsampling. ACM Trans. Graph. (TOG) 26, 96 (2007)CrossRef
  7.Levin, A., Lischinski, D., Weiss, Y.: Colorization using optimization. ACM Trans. Graph. (TOG) 23(3), 689–694 (2004)CrossRef
  8.Levin, A., Lischinski, D., Weiss, Y.: A closed-form solution to natural image matting. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 228–242 (2008)CrossRef
  9.Lischinski, D., Farbman, Z., Uyttendaele, M., Szeliski, R.: Interactive local adjustment of tonal values. ACM Trans. Graph. (TOG) 25, 646–653 (2006)CrossRef
  10.Pellacini, F., Lawrence, J.: Appwand: editing measured materials using appearance-driven optimization. ACM Trans. Graph. (TOG) 26, 54 (2007)CrossRef
  11.Wang, Y., Yang, J., Yin, W., Zhang, Y.: A new alternating minimization algorithm for total variation image reconstruction. SIAM J. Imaging Sci. 1(3), 248–272 (2008)MATH MathSciNet CrossRef
  12.Xu, K., Li, Y., Ju, T., Hu, S.M., Liu, T.Q.: Efficient affinity-based edit propagation using kd tree. ACM Trans. Graph. (TOG) 28, 118 (2009)
  13.Xu, L., Lu, C., Xu, Y., Jia, J.: Image smoothing via l 0 gradient minimization. ACM Trans. Graph. (TOG) 30(6), 174 (2011)
  14.Xu, L., Yan, Q., Jia, J.: A sparse control model for image and video editing. ACM Trans. Graph. (TOG) 32(6), 197 (2013)
  15. Zhang, Q., Shen, X., Xu, L., Jia, J.: Rolling guidance filter. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part III. LNCS, vol. 8691, pp. 815–830. Springer, Heidelberg (2014)
  
• 作者单位：Zhenyuan Guo (18)
  Haoqian Wang (18)
  Kai Li (18) (19)
  Yongbing Zhang (18)
  Xingzheng Wang (18)
  Qionghai Dai (18) (19)
  
  18. Graduate School at Shenzhen, Tsinghua University, Beijing, China
  19. Department of Automation, Tsinghua University, Beijing, China
  
• 丛书名：Advances in Multimedia Information Processing -- PCM 2015
• ISBN：978-3-319-24075-6
• 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

In this paper, we study how to perform edit propagation using \( L_0 \) gradient minimization. Existing propagation methods only take simple constraints into consideration and neglects image structure information. We propose a new optimization framework making use of \( L_0 \) gradient minimization, which can globally satisfy user-specified edits as well as tackle counts of non-zero gradients. In this process, a modified affinity matrix approximation method which efficiently reduces randomness is raised. We introduce a self-adaptive re-parameterization way to control the counts based on both original image and user inputs. Our approach is demonstrated by image recoloring and tonal values adjustments. Numerous experiments show that our method can significantly improve edit propagation via \( L_0 \) gradient minimization.