›› 2012, Vol. 27 ›› Issue (4): 830-840.doi: 10.1007/s11390-012-1267-3

• Regular Papers • Previous Articles     Next Articles

Edit Propagation via Edge-Aware Filtering

Wei Hu1 (胡伟), Zhao Dong2 (董朝), and Guo-Dong Yuan3 (袁国栋)   

  1. 1. Department of Computer Science and Technology, Beijing University of Chemical Technology, Beijing 100028, China;
    2. Program of Computer Graphics, Cornell University, Ithaca 14853, U.S.A.;
    3. Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
  • Received:2011-10-14 Revised:2012-01-09 Online:2012-07-05 Published:2012-07-05
  • Supported by:

    This work was supported by the National Natural Science Foundation of China under Grant No.61003132, the National High Technology Research and Development 863 Program of China under Grant No. 2010AA012400.

This paper presents a novel framework for efficiently propagating the stroke-based user edits to the regions with similar colors and locations in high resolution images and videos. Our framework is based on the key observation that the edit propagation intrinsically can also be achieved by utilizing recently proposed edge-preserving filters. Therefore, instead of adopting the traditional global optimization which may involve a time-consuming solution, our algorithm propagates edits with the aid of the edge-preserve filters. Such a propagation scheme has low computational complexity and supports multiple kinds of strokes for more flexible user interactions. Further, our method can be easily and efficiently implemented in GPU. The experimental results demonstrate the efficiency and user-friendliness of our approach.

[1] Levin A, Lischinski D, Weiss Y. Colorization using optimization.ACM Transactions on Graphics, 2004, 23(3): 689-694.

[2] Lischinski D, Farbman Z, Uyttendaele M, Szeliski R. Interactivelocal adjustment of tonal values. ACM Transactions onGraphics, 2006, 25(3): 646-653.

[3] Pellacini F, Lawrence J. Appward: Editing measured materialsusing appearance-driven optimization. ACM Transactionson Graphics, 2007, 26(3): Article No. 54:1-10.

[4] An X, Pellacini F. Appprop: All-pairs appearance-space editpropagation. ACM Transactions on Graphics, 2008, 27(3):Article No. 40:1-9.

[5] Xu K, Li Y, Ju T, Hu S, Liu T Q. Efficient affinity-based editpropagation using K-D tree. ACM Transactions on Graphics,2009, 28(5): Article No. 118:1-9.

[6] Xiao C, Nie Y, Tang F. Efficient edit propagation using hierarchicaldata structure. IEEE Transactions on Visualizationand Computer Graphics, 2011, 17(8): 1135-1147.

[7] Li Y, Ju T, Hu S. Instant propagation of sparse edits on imagesand videos. Computer Graphics Forum, 2010, 29(7):2049-2054.

[8] He K, Sun J, Tang X. Guided image filtering. In Proc. ECCV,Sept. 2010, pp.1-14.

[9] Gastal E S L, OliveiraM M. Domain transform for edge-awareimage and video processing. ACM Transactions on Graphics,2011, 30(4): Article No. 69:1-11.

[10] Xu K, Wang J, Tong X, Hu S, Guo B. Edit propagation onbidirectional texture functions. Computer Graphics Forum,2009, 28(7): 1871-1877.

[11] Criminisi A, Sharp T, Rother C, Pèrez P. Geodesic image andvideo editing. ACM Transactions on Graphics, 2010, 29(5):Article No. 134: 1-12.

[12] Ma L, Xu K. Antialiasing recovery for editing propagation.In Proc. ACM Siggraph VRCAI, Dec. 2011, pp.1-6.

[13] Bie X, Huang H, Wang W. Real time edit propagation byefficient sampling. Computer Graphics Forum, 2011, 30(7):2041-2048.

[14] Kin M H, Ritschel T, Kautz J. Edge-aware color appearance.ACM Trans. Graphics, 2011, 30(2): Article No. 13:1-9.

[15] Farbman Z, Fattal R, Lischinski D, Szeliski R. Edit-preservingdecompositions for multi-scale tone and detail manipulation.ACM Transactions on Graphics, 2008, 27(3): Article No.67:1-8.

[16] Levin A, Lischinski D,Weiss Y. A closed-form solution to naturalimage matting. IEEE Transactions on Pattern Analysisand Machine Intelligence, 2008, 30(2): 228-242.

[17] Farbman Z, Fattal R, Lischinski D. Diffusion maps for edgeawareimage editing. ACM Transactions on Graphics, 2010,29(6): Article No. 145:1-6.

[18] Perona P, Malik J. Scale-space and edge detection usinganisotropic diffusion. IEEE Transactions on Pattern Analysisand Machine Intelligence, 1990, 12(7): 629-639.

[19] Weickert J, Romeny B M, Viergever M A. Efficient and reliableschemes for nonlinear diffusion filtering. IEEE Transactionson Image Processing, 1998, 7(3): 398-410.

[20] Tomasi C, Manduchi R. Bilateral filtering for gray and colorimages. In Proc. the 6th ICCV, Jan. 1998, pp.839-846.

[21] Barash D. A fundamental relationship between bilateral filtering,adaptive smoothing, and the nonlinear diffusion equation.IEEE Transactions on Pattern Analysis and MachineIntelligence, 2002, 24(6): 844-847.

[22] Paris S, Hasinoff S W, Kautz J. Local laplacian filters: Edgeawareimage processing with a Laplacian pyramid. ACMTransactions on Graphics, 2011, 30(6): Article No. 68:1-10.

[23] Durand F, Dorsey J. Fast bilateral filtering for the display ofhigh-dynamic-range images. ACM Transactions on Graphics,2002, 21(3): 257-266.

[24] Chen J, Paris S, Durand F. Real-time edge-aware image processingwith the bilateral grid. ACM Transactions on Graphics,2007, 26(3): Article No. 103:1-11.

[25] Paris S, Durand F. A fast approximation of the bilateral filterusing a signal processing approach. International Journal ofComputer Vision, 2009, 81(1): 24-52.

[26] Fattal R. Edge-avoiding wavelets and their applications.ACM Trans. Graphics, 2009, 28(3): Article NO. 22:1-9.

[27] Li Y, Adelson E H, Agarwala A. Scribbleboost: Adding classificationto edge-aware interpolation of local image and videoadjustments. Computer Graphics Forum, 2008, 27(4): 1255-1264.

[28] Li Y, Sun J, Tang C, Shum H. Lazy snapping. ACM Transactionson Graphics, 2004, 23(3): 303-308.

[29] Rother C, Kolmogorov V, Blake A. “Grabcut” — Interactiveforeground extraction using iterated graph cuts. ACMTransactions on Graphics, 2004, 23(3): 309-314.

[30] Szeliski R, Zabih R, Scharstein D, Veksler O, Kolmogorov V,Agarwala A, Tappen M F, Rother C. A comparative study ofenergy minimization methods for Markov random fields withsmoothness-based priors. IEEE Trans. Pattern Analysis andMachine Intelligence, 2008, 30(6): 1068-1080.
No related articles found!
Full text



[1] Zhang Cui; Zhao Qinping; Xu Jiafu;. Kernel Language KLND[J]. , 1986, 1(3): 65 -79 .
[2] Lu Xuemiao;. On the Complexity of Induction of Structural Descriptions[J]. , 1987, 2(1): 12 -21 .
[3] Zhu Mingyuan;. Two Congruent Semantics for Prolog with CUT[J]. , 1990, 5(1): 82 -91 .
[4] Yang Hongqing;. A Characterization of Achievable Patterns of the MN-Puzzle Problem[J]. , 1990, 5(3): 266 -274 .
[5] Zhao Ming;. 2-D EAG Method for the Recognition of Hand-Printed Chinese Characters[J]. , 1990, 5(4): 319 -328 .
[6] Han Jianchao; Shi Zhongzhi;. Formalizing Default Reasoning[J]. , 1990, 5(4): 374 -378 .
[7] Ma Zhifang;. DKBLM——Deep Knowledge Based Learning Methodology[J]. , 1993, 8(4): 93 -98 .
[8] Jose K- Raphel; Siu Cheung Hui; Angela Goh;. Class Based Contextual Logic for DOOD[J]. , 1996, 11(2): 161 -170 .
[9] Chi-Ming CHUNG; Ding-An CHIANG; YANG Qing;. A Comparative Analysis of Different Arbitration Protocols for Multiple-Bus Multiprocessors[J]. , 1996, 11(3): 313 -325 .
[10] Ma Zongmin; Yan Li;. Using Multivalued Logic in Relational Database Containing Null Value[J]. , 1996, 11(4): 421 -426 .

ISSN 1000-9000(Print)

CN 11-2296/TP

Editorial Board
Author Guidelines
Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
E-mail: jcst@ict.ac.cn
  Copyright ©2015 JCST, All Rights Reserved