Alpha Matting Evaluation Website
www.alphamatting.com
Hide Help
How to use this page?
  1. Please be patient until all images have loaded completely.
  2. Move the mouse over the numbers in the table to see the corresponding images.
  3. Drag the red rectangle in the leftmost image to change the location of the zoom.
  4. Press and hold any key to temporarily deactivate the links.

Image matting evaluation results      Competition:   Low resolution  High resolution  
Error type:  SAD   MSE   Gradient   Connectivity  
Mean Squared Error overall
avg.
small
avg.
large
avg.
user
Troll
(Strongly Transparent)
Input  
Doll
(Strongly Transparent)
Input  
Donkey
(Medium Transparent)
Input  
Elephant
(Medium Transparent)
Input  
Plant
(Little Transparent)
Input  
Pineapple
(Little Transparent)
Input  
Plastic bag
(Highly Transparent)
Input  
Net
(Highly Transparent)
Input  
  rank rank rank rank small large user small large user small large user small large user small large user small large user small large user small large user
Information-flow matting4.363.13.90.3 1 0.4 1 0.5 3 0.3 8 0.4 6 0.5 10 0.3 4 0.3 3 0.2 5 0.1 11 0.1 4 0.1 5 0.4 13 0.4 2 0.6 1 0.2 4 0.3 2 0.3 2 1.3 4 1.2 4 0.8 1 0.8 3 0.8 3 0.9 4
DCNN Matting4.55.52.65.40.4 10 0.5 4 0.7 8 0.2 2 0.3 2 0.4 5 0.2 2 0.3 4 0.2 6 0.1 8 0.1 2 0.1 1 0.4 11 0.4 1 0.8 5 0.2 5 0.4 4 0.3 4 1.3 5 1.2 3 1 7 0.7 1 0.7 1 0.9 7
Deep Matting53.84.46.80.4 4 0.4 3 0.4 1 0.2 1 0.3 3 0.3 1 0.1 1 0.1 1 0.2 1 0 1 0 1 0.2 12 0.5 17 0.6 19 1 14 0.2 1 0.2 1 0.4 8 1.1 1 1.1 1 1.1 8 0.8 4 0.9 6 1 9
Three-layer graph model8.57.87.510.40.4 5 0.5 5 0.5 5 0.3 4 0.3 1 0.5 12 0.3 11 0.4 14 0.2 9 0.1 6 0.1 5 0.2 11 0.5 15 0.5 5 1.2 24 0.3 12 0.6 17 0.6 18 1.4 7 1.5 11 0.9 3 0.8 2 0.7 2 0.8 1
LNSP Matting10.67.910.313.60.5 14 1.9 31 1.2 33 0.2 3 0.4 5 0.5 16 0.3 9 0.4 16 0.2 4 0 2 0.1 6 0.2 14 0.4 12 0.5 6 0.8 4 0.2 2 0.3 3 0.4 9 1.4 10 1.2 5 0.8 2 1 11 1.1 10 1.5 27
Patch-based Matting11.6811.914.90.4 9 1.4 20 0.9 22 0.3 10 0.5 22 0.6 20 0.3 8 0.3 5 0.3 18 0 4 0.2 7 0.1 9 0.3 3 0.5 4 0.8 7 0.2 9 0.6 16 0.5 10 1.3 6 1.4 6 1.6 21 1 15 1.2 15 1.1 12
KL-Divergence Based Sparse Sampling13.112.611.914.80.4 7 0.9 10 0.7 7 0.3 9 0.5 15 0.5 15 0.3 26 0.4 11 0.3 15 0.1 7 0.2 13 0.1 2 0.4 9 0.4 3 1.2 21 0.4 18 0.6 15 0.6 21 1.7 19 2 24 2.1 31 0.8 6 0.8 4 0.9 6
CCM13.416.4149.80.5 18 1.2 17 0.8 18 0.3 15 0.5 19 0.5 11 0.3 5 0.4 13 0.2 2 0.1 19 0.2 8 0.1 4 0.5 23 0.6 15 0.7 3 0.3 10 0.4 6 0.3 3 1.7 18 1.8 21 1.5 20 1.2 23 1.2 13 1.3 17
Graph-based sparse matting13.814.114.312.90.5 20 1.5 23 0.8 11 0.3 7 0.3 4 0.3 3 0.3 19 0.4 19 0.3 12 0 3 0.2 9 0.1 8 0.5 16 0.5 8 0.9 9 0.2 6 0.6 12 0.5 12 2.2 29 2.4 31 1.9 29 1 13 1.1 8 1.3 19
TSPS-RV Matting14.314.611.317.10.4 3 0.8 8 0.5 4 0.3 12 0.4 9 0.6 25 0.3 17 0.3 10 0.3 14 0 5 0.1 3 0.3 32 0.8 32 0.6 14 1 17 0.5 26 0.6 13 0.8 29 1.6 14 1.6 14 1.4 14 0.8 8 1.3 19 0.9 2
SVR Matting14.61813.512.41.1 35 2.7 39 1.2 32 0.4 30 0.4 8 0.4 8 0.3 22 0.3 8 0.2 3 0.1 10 0.2 12 0.2 19 0.3 5 0.5 11 0.7 2 0.2 7 0.4 7 0.3 5 1.4 9 1.4 7 0.9 5 1.3 26 1.2 16 1.5 25
Comprehensive sampling14.713.514.915.60.4 8 1.2 18 0.8 12 0.3 19 0.6 24 0.6 29 0.3 21 0.3 7 0.3 20 0.1 12 0.2 10 0.1 6 0.2 1 0.5 12 0.9 11 0.3 15 0.9 22 0.5 13 1.6 15 1.5 9 1.5 16 1 17 1.2 17 1.3 18
Comprehensive Weighted Color and Texture15.414.91714.40.7 27 0.8 9 0.8 19 0.4 26 0.7 28 0.5 14 0.3 6 0.3 6 0.2 10 0.1 9 0.2 15 0.1 3 0.3 2 0.7 20 1 18 0.2 3 0.4 5 0.3 1 2.2 30 2.1 27 1.7 26 1 16 1.7 26 1.4 24
LocalSamplingAndKnnClassification16.518.114.916.60.5 15 0.7 6 0.5 2 0.3 5 0.4 10 0.5 18 0.3 7 0.3 9 0.2 8 0.1 14 0.2 17 0.2 18 0.9 34 1 29 1.7 31 0.6 30 1 26 0.9 30 1.8 20 1.5 10 1.2 11 1.1 20 1.2 12 1.2 15
CSC Matting1720.311.519.30.6 24 0.8 7 0.7 9 0.3 18 0.4 7 0.7 30 0.4 30 0.4 15 0.4 34 0.1 27 0.2 14 0.2 28 0.4 7 0.5 7 0.8 6 0.3 14 0.5 8 0.6 20 1.7 17 1.5 12 1.3 13 1.2 25 1.3 22 1.2 14
Sparse coded matting182019.414.50.6 26 2.7 38 0.8 17 0.3 17 0.4 13 0.3 2 0.3 27 0.4 24 0.3 23 0.1 18 0.2 11 0.1 7 0.4 6 0.5 9 0.9 8 0.2 8 0.5 9 0.3 6 2.3 31 2.6 33 2.1 30 1.3 27 1.3 18 1.4 23
Weighted Color and Texture Matting18.116.519.318.50.5 19 0.9 11 0.8 10 0.4 22 0.6 25 0.6 26 0.3 3 0.3 2 0.2 7 0.1 22 0.5 32 0.2 26 0.5 18 0.8 23 1.5 28 0.3 11 0.5 10 0.5 11 1.6 13 1.6 16 1.5 18 1.2 24 2.6 35 1.4 22
Global Sampling Matting18.914.822.419.50.4 6 2.3 34 0.9 21 0.3 13 0.6 23 0.6 27 0.3 13 0.4 28 0.3 11 0.1 15 0.3 23 0.2 22 0.5 19 0.6 13 1 15 0.4 20 1 25 0.7 24 1.9 22 2 26 1.7 25 0.9 10 1 7 1.1 11
LNCLM matting19.321.518.817.80.4 2 0.4 2 0.9 23 0.4 25 0.5 18 0.4 4 0.4 37 0.6 37 0.3 24 0.1 32 0.3 21 0.2 27 0.6 29 0.8 22 1.1 19 0.4 17 0.9 24 0.5 14 1.8 21 1.6 17 1.1 10 0.8 9 1.1 9 1.3 21
Iterative Transductive Matting19.520.618.519.40.6 22 0.9 12 0.8 16 0.3 11 0.7 26 0.6 24 0.4 32 0.4 18 0.3 19 0.1 23 0.5 34 0.2 24 0.6 25 0.6 18 1.4 27 0.4 24 0.8 20 0.7 23 1.9 23 1.6 15 1.5 19 0.8 5 0.9 5 0.9 3
Shared Matting2018.922.918.40.5 11 1.6 25 0.9 20 0.5 32 0.9 33 0.5 19 0.3 10 0.4 12 0.3 22 0.1 24 0.4 27 0.2 16 0.4 10 0.6 17 0.9 10 0.4 16 0.6 14 0.5 15 2.9 36 2.8 35 2.7 35 1 12 1.3 20 1 10
KNN Matting20.122.620.617.10.8 30 1 14 0.8 14 0.4 24 0.5 21 0.5 9 0.4 31 0.5 31 0.3 32 0.1 28 0.3 24 0.2 29 0.7 31 0.9 28 0.9 13 0.3 13 0.5 11 0.4 7 1.1 2 1.1 2 0.9 4 1.2 22 2.3 34 1.6 29
Improved color matting22.523.423.520.80.8 32 2.4 35 1.5 36 0.3 16 0.5 17 0.5 17 0.3 12 0.4 27 0.3 13 0.1 25 0.3 22 0.2 20 0.7 30 0.7 21 0.9 12 0.4 19 0.7 19 0.7 25 2 25 1.9 23 1.4 15 1.3 28 1.5 24 1.5 28
Segmentation-based matting22.723.322.522.40.5 21 2.2 32 1.1 27 0.3 20 0.4 11 0.4 6 0.3 18 0.4 26 0.3 16 0.1 13 0.2 16 0.2 10 0.6 26 0.5 10 1.2 25 0.4 23 0.7 18 0.8 28 2.7 34 3.3 38 3.6 37 1.4 31 1.9 29 1.6 30
Improving Sampling Criterion23.722.425.623.10.5 12 1.3 19 0.8 13 0.6 35 1 34 0.7 32 0.3 24 0.5 34 0.3 30 0.3 40 0.8 39 0.4 39 0.5 21 0.9 27 1.2 22 0.6 32 1.1 28 0.8 27 1.4 8 1.5 13 1.5 17 0.8 7 1.1 11 0.9 5
SRLO Matting24.323.925.523.50.7 29 1 13 1 24 0.4 28 0.8 32 0.7 31 0.4 29 0.4 21 0.3 31 0.1 29 0.6 35 0.2 23 0.4 14 0.8 24 1.5 29 0.4 22 1 27 0.6 19 2 26 2.3 29 1.7 23 1 14 1.4 23 1 8
Local Spline Regression (LSR)25.526.124.425.90.5 13 1.5 21 1 25 0.3 14 0.5 20 0.6 22 0.4 28 0.4 30 0.3 25 0.1 20 0.3 20 0.2 21 1.2 38 1.3 36 2.2 35 0.8 36 1.1 29 1.1 32 2.1 28 1.7 18 1.3 12 1.5 32 1.3 21 3 35
Learning Based Matting25.626.325.6250.8 33 1.6 24 1.3 34 0.4 27 0.4 14 0.5 13 0.3 20 0.4 25 0.3 21 0.1 21 0.2 18 0.2 15 0.5 24 1.2 32 2 33 0.9 38 1.7 37 2 39 1.6 12 1.7 19 1 6 2.2 35 2.7 36 4.2 39
Closed-Form Matting262425.628.50.5 17 1.8 30 1.1 29 0.3 6 0.4 12 0.6 21 0.3 15 0.4 23 0.3 17 0.1 16 0.3 19 0.2 17 1.2 37 1.4 37 2.3 38 0.8 35 1.6 36 1.6 37 3 37 2.7 34 1.9 28 1.3 29 1.2 14 5 41
LMSPIR26.125.626.6260.8 31 1.1 15 1.2 30 0.4 23 0.8 31 0.6 28 0.3 25 0.4 17 0.3 27 0.1 26 0.5 31 0.2 25 0.6 28 1.2 35 2 34 0.4 21 0.9 23 0.6 16 2.3 32 2.3 30 2.2 32 1.1 19 2 31 1.2 16
SPS matting26.424.431.123.60.5 16 1.6 26 0.6 6 0.7 36 1.1 36 0.7 33 0.4 36 0.6 38 0.4 35 0.2 38 0.9 40 0.3 33 0.4 8 0.8 26 1.2 23 0.5 27 1.2 31 0.6 17 1.7 16 2 25 1.7 22 1.1 18 1.7 27 1.3 20
Global Sampling Matting (filter version)26.924.828.127.80.6 23 2.4 36 1.1 28 0.5 31 0.7 29 0.7 35 0.4 34 0.5 33 0.4 36 0.2 33 0.4 26 0.3 35 0.3 4 0.6 16 1 16 0.5 28 1.2 32 0.8 26 2 24 2.2 28 2.4 33 1.2 21 1.5 25 1.1 13
Shared Matting (Real Time)28.628.42928.40.6 25 1.7 29 1 26 0.7 38 1.2 37 0.8 37 0.3 16 0.4 20 0.3 29 0.2 35 0.6 36 0.2 31 0.5 20 0.8 25 1.1 20 0.4 25 0.8 21 0.6 22 3 38 3 36 3 36 1.3 30 1.9 28 1.5 26
Large Kernel Matting29.431.828.927.61.2 37 1.6 27 1.7 37 0.3 21 0.5 16 0.4 7 0.4 33 0.5 32 0.3 33 0.1 30 0.5 33 0.2 30 0.9 35 1.1 31 1.4 26 0.6 31 1.1 30 1 31 2.7 33 2.4 32 1.7 24 2.1 34 2 30 2.8 33
Cell-based matting Laplacian30.93329.929.80.7 28 1.7 28 0.8 15 0.4 29 0.8 30 0.6 23 0.5 38 0.5 35 0.4 40 0.2 39 0.5 28 0.3 37 0.8 33 1 30 1.5 30 0.8 37 1.3 33 1.2 34 2 27 1.8 22 1.8 27 1.9 33 2.3 33 2.4 32
Robust Matting31273233.91.1 36 2.8 40 1.7 38 0.7 37 1.5 38 0.9 38 0.3 14 0.4 29 0.3 26 0.1 31 0.5 29 0.3 34 0.5 22 1.2 33 1.9 32 0.5 29 1.5 35 1.2 35 1.5 11 1.8 20 2.6 34 2.4 36 2.3 32 2.9 34
High-res matting32.83134.932.51.3 39 2.2 33 2.2 39 0.5 33 1.1 35 0.8 36 0.3 23 0.4 22 0.3 28 0.1 17 0.7 37 0.2 13 0.6 27 1.2 34 2.2 36 0.8 33 2 39 1.4 36 3.2 39 3.4 40 4.2 41 2.6 37 4.3 39 2.2 31
Transfusive Weights32.833.430.434.61.3 38 1.5 22 1.3 35 0.5 34 0.7 27 0.7 34 0.4 35 0.6 36 0.4 38 0.2 36 0.5 30 0.3 38 1.6 40 2 39 3.9 40 1.5 40 2.2 40 2.2 41 1.2 3 1.4 8 1.1 9 4.4 41 4.9 41 5.9 42
Random Walk Matting38.440.33638.91 34 1.1 16 1.2 31 1 39 1.7 39 1.1 39 0.5 41 0.6 39 0.6 41 0.2 37 0.4 25 0.3 36 2 44 3.4 42 4.2 42 1.6 42 2.3 41 2.1 40 4.6 43 4.4 43 4 39 8.3 42 9.4 43 8.5 43
Iterative BP Matting38.837.838.639.91.7 40 2.6 37 2.3 40 1.5 41 2.6 41 2.3 43 0.5 39 0.7 40 0.4 39 0.2 34 0.8 38 0.4 40 1.1 36 2 38 3.1 39 1 39 2 38 1.6 38 2.8 35 3.3 39 4.5 42 3 38 3.8 38 3.6 38
Geodesic Matting40.340.640.3402.4 42 4.6 43 3.4 43 1.5 40 1.8 40 1.9 40 1.6 44 2.1 45 1.1 43 0.8 44 1.9 43 0.9 44 1.8 41 2.5 40 2.2 37 0.8 34 1.4 34 1.1 33 3.3 40 3.2 37 4.1 40 3.8 40 4.3 40 4.2 40
Improved Bayesian41.541.641.541.43.3 44 3.8 42 3.8 44 2.1 42 2.8 42 2.1 41 0.5 40 1 42 0.4 37 0.3 41 1.2 41 0.7 43 1.6 39 4.2 43 5.4 44 1.5 41 3.4 43 2.3 42 4.3 42 4.3 42 4.8 44 11.5 44 3.2 37 3.3 36
Bayesian Matting42.342.343.141.53 43 4.6 44 3.4 42 2.3 43 3.2 43 2.1 42 1.4 43 1.5 43 1.2 45 0.7 43 2.1 44 0.6 41 1.8 42 4.2 44 5.2 43 2.2 44 4.6 44 2.9 44 3.4 41 3.9 41 3.9 38 3.7 39 8.6 42 3.5 37
Easy Matting42.642.842.542.52.2 41 3.7 41 3.3 41 2.4 44 3.2 44 2.9 44 0.7 42 0.9 41 0.6 42 0.5 42 1.4 42 0.6 42 1.8 43 2.5 41 4.1 41 1.7 43 2.7 42 2.4 43 5.4 44 5.4 44 4.7 43 10 43 15.9 45 16.3 44
Poisson Matting44.94544.844.96.9 45 7.5 45 7.1 45 4.7 45 7.7 45 5.3 45 1.7 45 1.9 44 1.1 44 1.6 45 2.5 45 1.4 45 3.5 45 6.3 45 11.5 45 3.6 45 5.7 45 3.9 45 6.1 45 9.4 45 6.8 45 19.4 45 11 44 21.6 45
Move the mouse over the numbers in the table to see the corresponding images.Click to compare with the ground truth. Press a key to deactivate the links (to better use the zoom).

Troll - Input image
Loading zoom, please wait Drag the window to change the zoom.

References

MethodReference and notesImplementation details
Closed-Form MattingA. Levin, D. Lischinski, Y. Weiss, A Closed Form Solution to Natural Image Matting, CVPR, 2006Matlab implementation on a Intel Core2 Quad with 2.4 GHZ
Bayesian MattingY.Y. Chuang, B. Curless, D. Salesin, R. Szeliski, A Bayesian Approach to Digital Matting, CVPR, 2001C++ implementation on a Intel Core2 Quad with 2.4 GHZ
Poisson MattingJ. Sun, J. Jia, C.K. Tang, H.Y. Shum, Poisson matting, SIGGRAPH, 2004Matlab implementation on a Intel Core2 Quad with 2.4 GHZ
Easy MattingY. Guan, W. Cheny, X. Liang, Z. Ding, Q. Peng, Easy Matting: A Stroke Based Approach for Continuous Image Matting, Eurographics, 2006C++ implementation on a Intel Core2 Quad with 2.4 GHZ
Random Walk MattingL. Grady, T. Schiwietz, S. Aharon, Random Walks For Interactive Alpha-Matting, VIIP, 2005Matlab/C++ implementation on a Intel Core2 Quad with 2.4 GHZ
Robust MattingJ. Wang, M. Cohen, Optimized Color Sampling for Robust Matting, CVPR, 2007C++ implementation on a Intel Core2 Quad with 2.4 GHZ
Geodesic MattingXue Bai, Guillermo Sapiro, A geodesic framework for fast interactive image and video segmentation and matting, ICCV 2007C++ implementation on a Intel Core2 Duo with 2.53 GHZ
Iterative BP MattingJue Wang, Michael Cohen, Jue Wang and Michael F. Cohen. An iterative optimization approach for unified image segmentation and matting. ICCV 2005.c++ implementation on a Intel Core2 Quad with 3 GHZ
Improved color mattingC. Rhemann, C. Rother, M. Gelautz, Improving Color Modeling for Alpha Matting. BMVC, 2008Matlab implementation on a Intel Core2 Duo with 2.4 GHZ
High-res mattingC. Rhemann, C. Rother, A. Rav-Acha, M. Gelautz, T. Sharp, High ResolutionMatting via Interactive Trimap Segmentation. CVPR, 2008Matlab/C++ implementation on a Intel Core2 Duo with 2.4 GHZ
Large Kernel MattingKaiming He, Jian Sun, and Xiaoou Tang, Fast Matting using Large Kernel Matting Laplacian Matrices, CVPR 2010C++ implementation on a Intel Core Duo with 2 GHZ
Segmentation-based mattingChristoph Rhemann, Carsten Rother, Pushmeet Kohli, Margrit Gelautz, A Spatially Varying PSF-based Prior for Alpha Matting, CVPR 2010Matlab/C++ implementation on a Intel Core2 Quad with 2.39 GHZ
Shared MattingEduardo S. L. Gastal and Manuel M. Oliveira, Shared Sampling for Real-Time Alpha Matting, Eurographics, 2010C++/GLSL implementation on a Core 2 Quad with 2.8 GHZ
Shared Matting (Real Time)Eduardo S. L. Gastal and Manuel M. Oliveira, Shared Sampling for Real-Time Alpha Matting, Eurographics, 2010C++/GLSL implementation on a Core 2 Quad with 2.8 GHZ
Learning Based MattingYuanjie Zheng, Chandra Kambhamettu, Yuanjie Zheng, Chandra Kambhamettu. Learning Based Digital Matting. ICCV 2009. SOURE CODEMatlab/C++ implementation on a Intel Core2 Duo with 2.53 GHZ
LMSPIRBei He, Guijin Wang, Zhiwei Ruan, Xuanwu Yin, Xiaokang Pei, Xinggang Lin, Local Matting based on Sample-pair Propagation and Iterative Refinement, ICIP 2012C++ implementation on a Intel Core2 Dual with 2 GHZ
SVR MattingZhanpeng Zhang, Qingsong Zhu, Yaoqin Xie, Learning Based Alpha Matting using Support Vector Regression, ICIP 2012Matlab implementation on a Intel Pentium Dual-Core with 3 GHZ
Cell-based matting LaplacianChen-Yu Tseng and Sheng-Jyh Wang, A cell-based matting Laplacian for contrast enhancement, ICIP 2012C++ implementation on a Intel Core i3 with 3 GHZ
Global Sampling MattingKaiming He, Christoph Rhemann, Carsten Rother, Xiaoou Tang, and Jian Sun, A Global Sampling Method for Alpha Matting, CVPR 2011C++ implementation on a Intel Core2 with 2 GHZ
Global Sampling Matting (filter version)Kaiming He, Christoph Rhemann, Carsten Rother, Xiaoou Tang, and Jian Sun, A Global Sampling Method for Alpha Matting, CVPR 2011 (using the guided filter in "Guided Image Filtering", ECCV 2010, by Kaiming He, Jian Sun, and Xiaoou Tang )C++ implementation on a Intel Core2 with 2 GHZ
Local Spline Regression (LSR)Shiming Xiang, Feiping Nie, Changshui Zhang, Semi-Supervised Classification via Local Spline Regression. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 11, pp. 2039-2053, 2010C++ implementation on a Intel Core2 with 3 GHZ
Weighted Color and Texture MattingE.Shahrian and D.Rajan, Weighted Color and Texture Sample Selection for Image Matting , CVPR 2012. matlab implementation on a Intel(R) Xeon(R) with 2.93 GHZ
KNN MattingQifeng Chen, Dingzeyu Li, Chi-Keung Tang, KNN Matting, CVPR 2012Matlab implementation on a Intel Core 2 Duo with 2.13 GHZ
SRLO MattingBei He, Guijin Wang, Xuanwu Yin, Bo Liu, Chenbo Shi, Xinggang Lin, High-accuracy and Quick Matting based on Sample-pair Refinement and Local Optimization, IEICE trans. on Information & Systems, 2013C++ implementation on a Intel Core2 Dual with 2 GHZ
LNSP MattingXiaowu Chen, Dongqing Zou, Ping Tan, Image Matting with Local and Nonlocal Smooth Priors, CVPR 2013matlab implementation on a intel core2 with 2.2 GHZ
CCMYongfang Shi, Au, O.C., Jiahao Pang, Tang, K., Wenxiu Sun, Hong Zhang, Wenjing Zhu, and Luheng Jia, Color Clustering Matting, ICME2013.Matlab implementation on a Intel Core i7 with 2.8 GHZ
Iterative Transductive MattingBei He, Guijin Wang, Chenbo Shi, Xuanwu Yin, Bo Liu, Xinggang Lin, Iterative Transductive Matting, ICIP 2013Matlab implementation on a Intel Core2 Dual with 2.2 GHZ
Improving Sampling CriterionJun Cheng, Zhenjiang Miao, Improving Sampling Criterion for Alpha Matting, RACVPR2013 in Conjunction with ACPR2013C++ implementation on a Core i5 with 2.5 GHZ
Transfusive WeightsKaan Yucer, Alexander Sorkine-Hornung, and Olga Sorkine-Hornung, Transfusive Weights for Content-Aware Image Manipulation, VMV2013Matlab implementation on a Quad-Core Intel Xeon with 3.2 GHZ
Comprehensive samplingE.Shahrian, D.Rajan, B.Price, S.Cohen, Improving Image Matting using Comprehensive Sampling Sets, CVPR 2013.Matlab implementation on a Intel Xeon with 2.4 GHZ
Comprehensive Weighted Color and TextureE.Shahrian , D.Rajan, Weighted Color and Texture Sample Selection for Image Matting, IEEE Transaction on Image Processing , Volume:PP, Issue: 99 , 2013. Matlab implementation on a Intel i7 with 3.5 GHZ
SPS mattingAhmad Al-Kabbany and Eric Dubois, "Improved global-sampling matting using sequential pair-selection strategy", In Proc. Visual Information Processing andCommunication V(SPIE), San Francisco, February 2014.Matlab implementation on a Intel Core2 Quad with 2.66 GHZ
Improved BayesianWenshuang Tan, Automatic Matting of Identification Photos, CAD/Graphics, 2013C++ implementation on a Intel Core(TM)i7-2600 with 3.4 GHZ
Sparse coded mattingJubin Johnson, Deepu Rajan, Hisham Cholakkal, Sparse Codes as Alpha Mattes, BMVC 2014.Matlab implementation on a Intel Xeon with 3.2 GHZ
LNCLM mattingB.-K. Kim, M. Jin, W.-J Song, Local and Nonlocal Color Line Models for Image Matting, IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, vol. E97-A. no.8, pp. 1814-1819, Aug. 2014.MATLAB implementation on a Intel Core i5-3570 with 3.4 GHZ
Graph-based sparse mattingJubin Johnson, Ehsan Shahrian Varnousfaderani, Hisham Cholakkal, and Deepu Rajan, Sparse Coding for Alpha Matting, IEEE Transactions on Image Processing, Volume: PP, Issue: 99, 2016.Matlab implementation on a Intel Xeon with 3.2 GHZ
KL-Divergence Based Sparse SamplingLevent Karacan, Aykut Erdem and Erkut Erdem, Image Matting with KL-Divergence Based Sparse Sampling,IEEE International Conference on Computer Vision(ICCV) 2015)Matlab implementation on a Intel Xeon(R) CPU E5-2620 with 2 GHZ
LocalSamplingAndKnnClassificationXiao Chen, Fazhi He, A Sampling-Propagation Matting Method Based on the Sample Validity and KNN Classification Labeling, Journal of Computer-Aided Design and Computer Graphics (CADCG), vol. 28(12), pp. 2186-2194, 2016.matlab implementation on a intel i3 2120 with 3.3 GHZ
DCNN MattingDonghyeon Cho, Yu-Wing Tai, Inso Kweon, Natural Image Matting using Deep Convolutional Neural Networks. ECCV 2016matlab implementation on a Intel Core i7 with 3.4 GHZ
CSC MattingXiaoxue Feng, Xiaohui Liang, Zili Zhang, A Cluster Sampling Method for Image Matting via Sparse Coding. ECCV 2016 Matlab implementation on a Intel(R) Core(TM) i5-3470 with 3.2 GHZ
Patch-based MattingGuangying Cao, Jianwei Li, Zhiqiang He, Xiaowu Chen, Divide and Conquer: A Self-Adaptive Approach for High-Resolution Image Matting. International Conference on Virtual Reality and Visualization (ICVRV 2016)matlab implementation on a i7 with 3.6 GHZ
TSPS-RV MattingAhmad Al-Kabbany and Eric Dubois, Matting with Sequential Pair Selection Using Graph Transduction. The 21st International Symposium on Vision, Modeling, and Visualization (VMV 2016)Matlab implementation on a Intel Core2 Quad with 2.66 GHZ
Deep Mattinganonymous, anonymous CVPR 2017 submissionMatlab implementation on a I7 with 2.7 GHZ
Information-flow mattingAnonymous, CVPR 2017 Submission #23Matlab implementation on a Intel Xeon with 3.5 GHZ
Three-layer graph modelChao Li, Ping Wang, Xiangyu Zhu, Huali Pi, Submitted to Computer Vision and Image UnderstandingC++, Matlab implementation on a Intel Xeon E5-2620 v3 with 2.4 GHZ