Alpha Matting Evaluation Website

Image Matting Evaluation•Datasets•Code•Submit

How to use this page?

Please be patient until all images have loaded completely.
Move the mouse over the numbers in the table to see the corresponding images.
Drag the red rectangle in the leftmost image to change the location of the zoom.
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

Sum of Absolute Differences 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

FE2E High-Quality Matting 3.3 3 3 3.9 10.1 1 11.1 1 9.3 1 5.5 6 6.4 4 6.9 6 3.4 2 3.7 2 3.2 4 1 2 1.7 2 1.9 1 5.7 7 7.8 7 11 11 2.5 1 3.8 2 3.8 1 17.3 2 18.4 2 17.4 6 19.6 3 21.8 4 20.2 1

Deep Matting 4.4 5.4 3.4 4.4 10.7 3 11.2 3 11 2 4.8 1 5.8 3 5.6 1 2.8 1 2.9 1 2.9 1 1.1 3 1.1 1 2 3 6 16 7.1 3 8.9 4 2.7 2 3.2 1 3.9 2 19.2 5 19.6 6 18.7 7 21.8 12 23.9 9 24.1 15

Information-flow matting 4.8 5.9 4.3 4.3 10.3 2 11.2 2 12.5 4 5.6 10 7.3 8 7.3 8 3.8 3 4.1 4 3 3 1.4 5 2.3 4 2 4 5.9 13 7.1 4 8.6 2 3.6 4 5.7 3 4.6 5 18.3 4 19.3 4 15.8 2 20.2 6 22.2 5 22.3 6

Superpixel-affinity matting 5.7 5.3 5.8 6 12.2 16 18.6 18 14.7 12 5 3 5.3 1 6.4 3 3.9 5 4 3 3 2 1.4 4 2.4 5 1.9 2 5.2 1 6.4 1 8.5 1 3.6 3 6.4 5 4.6 4 21.2 9 22.5 12 20.4 14 19.3 1 19.1 1 22.9 10

DCNN Matting 6.2 8 4.3 6.4 12 13 14.1 6 14.5 10 5.3 4 6.4 5 6.8 5 3.9 6 4.5 6 3.4 6 1.6 11 2.5 6 2.2 7 6 15 6.9 2 9.1 5 4 7 6 4 5.3 7 19.9 6 19.2 3 19.1 9 19.4 2 20 2 21.2 2

Three-layer graph matting 10.8 7.5 8.1 16.8 10.7 4 15.2 7 13.8 7 4.9 2 5.6 2 8.1 20 3.9 4 4.4 5 3.6 9 1 1 1.8 3 3 21 5.9 11 7.3 6 12.4 21 4.2 10 8 12 8.5 30 24.2 21 25.6 22 24.2 22 20.5 7 23.5 8 22.2 4

ATPM Matting 13.8 17.1 15.3 8.9 14 31 17.8 14 13.4 5 5.5 5 6.4 6 7.3 9 5.4 38 6.4 33 4.3 26 1.7 14 3.3 12 2.3 10 6.8 24 8 10 8.7 3 4.2 8 7.5 9 5.5 8 17.2 1 17.6 1 15.7 1 22.6 16 37.3 37 22.8 9

Three Stages Matting 13.8 13.6 13.8 13.9 11.7 12 13.9 5 13.9 8 5.6 7 7.4 10 7.9 14 4.6 18 5.5 19 4.2 20 2.2 27 4 19 3.1 26 6.5 21 11 31 11.9 16 4 5 6.5 6 4.5 3 23.3 15 23.2 17 22.3 17 19.6 4 20.8 3 22.4 7

CSC Matting 14.8 18.6 10.8 15 13.6 28 15.6 8 14.5 9 6.2 18 7.5 11 8.1 21 4.6 19 4.8 8 4.2 23 1.8 17 2.7 7 2.5 12 5.5 6 7.3 5 9.7 6 4.6 14 7.6 10 6.9 17 23.7 17 23 15 21 15 26.3 30 27.2 22 25.2 17

LNSP Matting 15.4 11.8 15.3 19.3 12.2 14 22.5 34 19.5 39 5.6 8 8.1 13 8.8 31 4.6 16 5.9 24 3.6 8 1.5 8 3.5 15 3.1 25 6.2 17 8.1 12 10.7 10 4 6 7.1 7 6.4 13 21.5 10 20.8 7 16.3 3 22.5 15 24.4 10 27.8 25

Graph-based sparse matting 16 16.6 16.6 14.8 12.6 20 20.5 26 14.8 16 5.7 12 7.3 7 6.4 4 4.5 14 5.3 15 3.7 10 1.4 7 3.3 13 2.3 9 6.3 19 7.9 8 11.1 12 4.2 9 8.3 15 6.4 12 28.7 34 31.3 35 27.1 31 23.6 18 25.1 14 27.3 24

Patch-based Matting 16.1 10.8 17.8 19.8 10.9 6 19 19 15.7 22 6 15 9.5 27 8.3 23 4.3 10 5.2 12 4.2 22 1.6 10 3.2 10 2.6 13 5.2 2 9 19 12.4 18 4.7 15 9.7 22 7 18 21.6 11 21.7 8 24.9 24 23.5 17 28.1 25 25.6 18

KL-Divergence Based Sparse Sampling 16.7 15.8 15.8 18.5 11.6 11 17.5 13 14.7 13 5.6 9 8.5 18 8 16 4.9 31 5.3 13 3.7 11 1.5 9 3.5 14 2.1 5 5.8 9 8.3 13 14.1 29 5.6 26 9.3 20 8 26 24.6 22 27.7 29 28.9 34 20.7 9 22.7 6 23.9 14

TSPS-RV Matting 17.6 16.3 16.8 19.9 11.3 10 16.4 11 13.7 6 6.1 16 8.1 15 8.6 28 4.5 12 5.4 17 4.1 19 1.4 6 3.3 11 3.5 35 7.9 34 8.9 17 12.4 20 6.2 30 9 18 8.7 32 22.8 14 23.5 18 21.4 16 20.7 8 28.5 27 22.2 3

Iterative Transductive Matting 18.5 19.9 18.1 17.5 13.1 25 17.2 12 15.6 21 5.7 11 8.6 20 7.8 13 5.1 34 5.5 18 3.9 12 1.9 18 5.8 31 2.6 14 6.6 22 8.5 15 13.8 28 5.4 20 10 23 7.4 23 25.5 24 24 19 23.8 21 20.1 5 22.7 7 22.7 8

Comprehensive sampling 18.6 16 18.5 21.4 11.2 9 18.5 17 14.8 14 6.5 24 9.5 26 8.9 33 4.5 13 4.9 9 4.1 18 1.7 13 3.1 9 2.3 11 5.4 5 9.8 23 13.4 26 5.5 24 11.5 30 7.4 25 23.9 19 22 10 22.8 18 23.8 21 28 24 28.1 26

SVR Matting 18.8 21.6 18.6 16 18.7 43 30.7 45 19.1 36 6.8 30 7.7 12 7.6 12 4.7 25 5 11 3.4 5 1.9 19 4.7 23 2.9 19 5.8 8 8.7 16 10.5 7 4.3 11 8 13 5.6 10 21.2 8 22.1 11 17.1 5 25.6 29 26.1 18 30.6 34

Comprehensive Weighted Color and Texture 19.1 19.3 19.8 18.3 14.6 32 16 9 15.7 23 6.8 29 10 30 7.9 15 4.3 9 5 10 4.1 16 1.7 12 3.5 16 2.2 6 5.4 4 9.9 25 12.8 24 4.3 12 7.4 8 5.2 6 28.3 33 28.1 30 25.4 27 24 23 30.2 30 28.7 29

Sparse coded matting 19.6 23.1 20.4 15.4 13.7 29 25.8 41 14.8 17 6.4 21 8.2 16 6.2 2 4.7 20 5.4 16 4 14 1.8 16 3.1 8 2.3 8 5.9 12 8 11 10.6 8 4.5 13 8 11 5.5 9 30.3 37 33.1 39 29.2 35 27.7 37 27.2 21 29 30

LocalSamplingAndKnnClassification 21.1 23.8 18.9 20.6 12.6 19 16 10 12.4 3 5.8 13 8.1 14 8 17 4.5 15 5.5 20 4.1 15 2.2 28 5.1 26 3.4 33 8.1 35 10.5 27 15.6 34 7.3 34 12.3 33 9.4 33 24.1 20 21.8 9 19.7 10 24.7 26 24.8 12 25.9 20

Weighted Color and Texture Matting 21.6 19.4 23.5 21.9 13.1 26 17.8 15 15.8 24 6.5 23 9.4 24 8.6 27 4.2 8 4.7 7 3.9 13 1.7 15 6 32 2.7 15 6.4 20 11 30 16.3 35 4.8 16 9.1 19 6.5 14 23.7 16 24.8 21 23.2 19 26.5 31 40.2 40 28.5 28

CCM 21.9 25.1 21.6 18.9 13.8 30 20.8 27 16.9 32 6.4 22 8.9 22 8.2 22 4.7 21 5.9 25 3.6 7 2.5 32 4.3 20 3 20 7 26 9 18 10.6 9 4.9 17 8.1 14 5.7 11 25.6 25 27.5 28 24.5 23 25.4 28 26.4 19 28.2 27

Shared Matting 22.4 20.6 26 20.5 10.8 5 20.5 25 15 18 7.8 36 11.6 37 8.1 18 4.2 7 5.3 14 4.2 21 2.1 21 5.8 30 2.9 18 5.9 14 9.2 20 11.4 14 5 18 8.8 16 6.8 16 34.9 42 34.9 40 34.3 40 23.9 22 28.4 26 25.7 19

LNCLM matting 22.5 25 22.1 20.3 10.9 7 11.2 4 16.7 30 6.9 32 8.9 23 7.2 7 5.6 40 7 41 4.1 17 2.5 34 5.1 27 3.5 36 7.5 29 10 26 12 17 5.5 25 11.3 27 7.3 22 25.2 23 23 16 19.9 12 21.2 10 25 13 26.4 21

PDMS 24 23.5 24.8 23.6 12.9 24 19.3 20 14.6 11 6.2 19 10.2 32 8.5 25 4.8 29 6.1 28 4.2 24 2.1 23 4.4 21 3.1 24 5.3 3 8.3 14 11.7 15 5.5 22 11 26 7.1 21 29.6 35 32.2 37 31.6 38 26.8 33 27.1 20 29.1 31

Global Sampling Matting 25.1 21.8 27.6 26 10.9 8 22.7 35 15.4 19 6.3 20 9.5 28 9 34 4.7 22 6.4 35 4.3 28 2.2 29 5.6 29 3.4 32 6.9 25 9.6 22 12.9 25 6.3 31 12.5 34 8.6 31 25.8 26 27.5 27 25.3 26 22 13 24.4 11 23.7 13

Segmentation-based matting 26 26.9 25 26.3 12.8 23 23.5 37 16.6 29 6.6 25 8.3 17 7.3 10 4.8 30 6.1 29 4.3 29 2.1 22 3.9 18 3.1 23 6.7 23 8 9 13.4 27 6 29 8.8 17 8.2 27 31.6 38 35.6 41 38.8 42 24.5 25 32 32 26.7 23

SRLO Matting 26 24.9 28 25.3 14.7 33 18 16 17.7 34 6.9 31 10.7 33 8.9 32 4.9 32 5.7 22 4.7 36 2.1 24 6.5 33 2.8 17 6.3 18 10.9 29 15.2 33 5.4 19 11.6 31 7 20 26.5 31 29.7 32 25.1 25 21.7 11 28.5 28 22.3 5

Improved color matting 27.2 27.3 26.4 27.9 14.9 34 24.5 39 20 40 6.7 27 9.5 25 8.5 26 4.6 17 6.1 30 4.3 30 2.6 36 5.4 28 3.4 34 7.5 30 9.9 24 12.5 22 6 27 10.1 24 8.4 29 26.1 27 26.7 26 23.6 20 23.8 20 25.6 15 26.7 22

Local Spline Regression (LSR) 27.5 29.8 24.1 28.8 12.2 15 20 23 16.2 25 6.1 17 8.8 21 8.1 19 5.2 36 6.2 32 4.6 33 2.2 30 4.9 25 3.1 27 9.4 40 11.9 34 18.3 38 8.2 37 11.4 28 10.1 35 26.4 29 22.5 13 20.2 13 27 34 26 17 39.8 40

KNN Matting 28 30.1 29.4 24.5 16.2 38 19.7 21 16.8 31 8 37 11 34 9 36 4.7 23 6.7 38 4.3 25 3 39 7.7 39 3.7 37 9.2 38 11.3 32 11.3 13 6 28 10.4 25 6.7 15 18.1 3 19.6 5 17 4 27.4 35 41 41 32.7 35

Global Sampling Matting (filter version) 28.1 26 30.4 28 12.3 17 24.3 38 16.3 26 7.3 34 10.2 31 9.5 37 5.1 35 6.4 34 4.7 37 2.4 31 4.7 24 3.2 29 5.9 10 9.5 21 12.4 19 6.5 32 13.1 35 8.3 28 26.5 30 28.3 31 30 37 23.6 19 29.1 29 23.5 11

Learning Based Matting 28.8 29.4 27.9 29.3 16 37 22 33 18.7 35 6.6 26 7.4 9 7.4 11 4.8 27 6.1 27 4.3 31 2.1 20 3.7 17 2.8 16 7.5 31 14.5 40 19.5 41 8.6 41 14.1 38 14.6 43 22.5 12 24.8 20 19.9 11 34.6 41 38.5 39 51.2 46

LMSPIR 30.1 29.1 31.6 29.6 15.2 36 20 22 19.1 37 6.7 28 11.2 35 8.7 30 4.8 28 5.8 23 4.6 35 2.1 25 6.8 36 3 22 7.9 33 14.3 39 20.2 42 5.5 23 11.4 29 7 19 29.7 36 31 34 29.6 36 24 24 34.2 35 25 16

Shared Matting (Real Time) 30.4 29 31.3 31 12.4 18 21.6 29 16.3 27 9.5 40 13.5 39 9.9 38 4.4 11 5.6 21 4.4 32 2.5 35 6.8 37 3.2 30 7.1 27 10.8 28 12.6 23 5.4 21 9.7 21 7.4 24 35.5 44 35.8 42 35.5 41 27.6 36 33.4 33 29.8 33

Closed-Form Matting 30.9 29.4 28.5 34.8 12.7 21 21.9 32 17.2 33 5.9 14 8.5 19 8.6 29 4.7 24 6 26 4.3 27 2.2 26 4.6 22 3.3 31 9.3 39 12.1 35 19.3 40 8.3 38 14.9 40 13.4 42 34.2 41 32.4 38 27.4 32 26.5 32 25.7 16 48.3 44

Improving Sampling Criterion 34.9 33.9 36.5 34.4 12.7 22 21.1 28 16.4 28 11.5 43 17 44 12.1 43 5.8 42 8.1 44 5.7 42 5.4 47 12.1 46 6.6 46 9.6 42 15.7 41 17.8 36 10.2 43 17 41 11.2 40 23.8 18 26.7 25 25.9 28 22.2 14 27.3 23 23.7 12

Cell-based matting Laplacian 35.1 37.3 33.9 34.3 15.1 35 21.7 30 15.6 20 7.6 35 11.4 36 9 35 5.7 41 6.7 39 5.2 40 3.1 40 6.7 34 4.5 40 8.6 36 11.4 33 14.9 31 8.5 40 13.5 37 11.1 38 27.7 32 26.2 24 27.6 33 32.4 39 37.6 38 37.9 37

Large Kernel Matting 35.3 37.1 34.6 34.3 17.2 39 21.8 31 20.7 41 7.2 33 9.6 29 8.4 24 5.3 37 6.6 37 4.6 34 2.9 38 8.2 41 4.2 38 8.6 37 12.1 36 14.7 30 8 36 13.4 36 11.2 39 33 39 31.8 36 26.1 29 32.1 38 32 31 38.4 39

Robust Matting 36.1 32.3 37 39 17.3 40 28.4 43 21.1 42 10.1 41 16.9 43 11.4 41 4.8 26 6.5 36 5 39 2.8 37 7.3 38 4.4 39 7.3 28 14 38 18.1 37 6.8 33 14.6 39 10.6 37 22.7 13 26.1 23 32.1 39 34.4 40 37 36 38 38

SPS matting 38.1 37.5 41.1 35.8 13.4 27 23 36 14.8 15 12.5 44 18.5 45 12.4 44 6.6 46 9.4 47 6.5 47 4.5 45 12.7 47 5.4 43 9.5 41 16.4 43 18.6 39 9.8 42 18.1 44 10.6 36 26.1 28 30.9 33 26.2 30 25 27 33.5 34 29.5 32

High-res matting 39.2 37.8 40.5 39.4 18.6 42 25.8 40 24.6 44 8.6 38 14.1 40 11.1 40 5 33 6.2 31 4.8 38 2.5 33 8.3 42 3.2 28 7.8 32 14 37 21.4 43 8.5 39 18.1 45 12.2 41 35.3 43 38.1 44 42.6 45 38.7 42 54.6 45 36.8 36

Transfusive Weights 39.6 39.5 39.4 40 23.2 44 26.7 42 22.4 43 9.2 39 11.9 38 10.4 39 6.1 44 8.1 43 5.9 44 3.8 43 8 40 5.3 42 12.9 45 21.4 45 37.6 49 13.1 48 22.8 47 18.3 48 20.9 7 22.9 14 19 8 59.5 46 65.7 46 72.8 47

Random Walk Matting 42.9 44.5 40.5 43.8 17.9 41 20.3 24 19.4 38 11.3 42 15.6 41 11.8 42 5.8 43 7 40 6.3 46 3.4 41 6.7 35 4.6 41 13.1 47 22.1 46 27.4 45 12.3 47 18 43 15.7 46 44.1 48 43.5 47 41 44 75.1 47 81.8 48 80.6 48

Geodesic Matting 44.1 45 43.9 43.5 26.9 47 38.5 48 32.5 47 14.2 45 16.5 42 17.4 46 11.7 49 14 50 9.4 49 7.6 49 15.1 48 8.7 49 12.8 44 16.7 44 15.1 32 7.3 35 12.1 32 9.8 34 37.3 46 37.4 43 42.8 46 48.6 45 50 44 48.6 45

Iterative BP Matting 45.2 44.5 45.1 46 23.6 45 29.9 44 27.2 45 16.7 46 24.3 47 20.7 49 6.7 47 9 45 6.3 45 3.8 42 11.3 44 6.8 48 14.1 48 22.8 47 27.9 46 11.4 45 19 46 14.7 44 33.4 40 39.3 45 47.5 49 40.6 43 48.1 43 45.1 42

Easy Matting 45.6 46 45 45.9 23.9 46 32.6 46 30 46 17.1 47 21.8 46 19.4 48 6.3 45 7.5 42 5.8 43 4.7 46 10.5 43 5.6 44 12.1 43 15.7 42 22.9 44 11.2 44 17 42 14.8 45 49.5 49 49.6 49 46.2 48 77.8 48 108.6 50 109.2 49

Improved Bayesian 46.1 46 46.5 45.9 31.2 49 34.9 47 33.9 49 17.8 48 24.4 48 17.2 45 5.5 39 9.3 46 5.3 41 3.9 44 11.4 45 6.6 47 13 46 29.5 48 34.6 48 11.9 46 24.5 48 16.1 47 42.9 47 44.6 48 46 47 92.4 49 46.5 42 45.4 43

Bayesian Matting 47.4 47.5 48.4 46.3 30.3 48 42.4 49 33.4 48 19.2 49 25.8 49 18.4 47 10.8 48 12.4 48 10.8 50 6.6 48 18.5 50 6.2 45 14.2 49 29.8 49 33.2 47 15.4 49 30.6 49 19.7 49 35.8 45 40.6 46 39.6 43 45.3 44 76.8 47 43.6 41

Poisson Matting 49.8 50 49.6 49.8 51.8 50 56.2 50 52 50 28.3 50 43.5 50 30.7 50 12.1 50 13.7 49 9.2 48 11.7 50 18.4 49 11.2 50 22.4 50 36.8 50 55.5 50 21.4 50 32.2 50 22.7 50 53.6 50 72.9 50 58.4 50 125.5 50 84.8 49 139.7 50

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).

Sum of Absolute Differences	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
FE2E High-Quality Matting	3.3	3	3	3.9	10.1 1	11.1 1	9.3 1	5.5 6	6.4 4	6.9 6	3.4 2	3.7 2	3.2 4	1 2	1.7 2	1.9 1	5.7 7	7.8 7	11 11	2.5 1	3.8 2	3.8 1	17.3 2	18.4 2	17.4 6	19.6 3	21.8 4	20.2 1
Deep Matting	4.4	5.4	3.4	4.4	10.7 3	11.2 3	11 2	4.8 1	5.8 3	5.6 1	2.8 1	2.9 1	2.9 1	1.1 3	1.1 1	2 3	6 16	7.1 3	8.9 4	2.7 2	3.2 1	3.9 2	19.2 5	19.6 6	18.7 7	21.8 12	23.9 9	24.1 15
Information-flow matting	4.8	5.9	4.3	4.3	10.3 2	11.2 2	12.5 4	5.6 10	7.3 8	7.3 8	3.8 3	4.1 4	3 3	1.4 5	2.3 4	2 4	5.9 13	7.1 4	8.6 2	3.6 4	5.7 3	4.6 5	18.3 4	19.3 4	15.8 2	20.2 6	22.2 5	22.3 6
Superpixel-affinity matting	5.7	5.3	5.8	6	12.2 16	18.6 18	14.7 12	5 3	5.3 1	6.4 3	3.9 5	4 3	3 2	1.4 4	2.4 5	1.9 2	5.2 1	6.4 1	8.5 1	3.6 3	6.4 5	4.6 4	21.2 9	22.5 12	20.4 14	19.3 1	19.1 1	22.9 10
DCNN Matting	6.2	8	4.3	6.4	12 13	14.1 6	14.5 10	5.3 4	6.4 5	6.8 5	3.9 6	4.5 6	3.4 6	1.6 11	2.5 6	2.2 7	6 15	6.9 2	9.1 5	4 7	6 4	5.3 7	19.9 6	19.2 3	19.1 9	19.4 2	20 2	21.2 2
Three-layer graph matting	10.8	7.5	8.1	16.8	10.7 4	15.2 7	13.8 7	4.9 2	5.6 2	8.1 20	3.9 4	4.4 5	3.6 9	1 1	1.8 3	3 21	5.9 11	7.3 6	12.4 21	4.2 10	8 12	8.5 30	24.2 21	25.6 22	24.2 22	20.5 7	23.5 8	22.2 4
ATPM Matting	13.8	17.1	15.3	8.9	14 31	17.8 14	13.4 5	5.5 5	6.4 6	7.3 9	5.4 38	6.4 33	4.3 26	1.7 14	3.3 12	2.3 10	6.8 24	8 10	8.7 3	4.2 8	7.5 9	5.5 8	17.2 1	17.6 1	15.7 1	22.6 16	37.3 37	22.8 9
Three Stages Matting	13.8	13.6	13.8	13.9	11.7 12	13.9 5	13.9 8	5.6 7	7.4 10	7.9 14	4.6 18	5.5 19	4.2 20	2.2 27	4 19	3.1 26	6.5 21	11 31	11.9 16	4 5	6.5 6	4.5 3	23.3 15	23.2 17	22.3 17	19.6 4	20.8 3	22.4 7
CSC Matting	14.8	18.6	10.8	15	13.6 28	15.6 8	14.5 9	6.2 18	7.5 11	8.1 21	4.6 19	4.8 8	4.2 23	1.8 17	2.7 7	2.5 12	5.5 6	7.3 5	9.7 6	4.6 14	7.6 10	6.9 17	23.7 17	23 15	21 15	26.3 30	27.2 22	25.2 17
LNSP Matting	15.4	11.8	15.3	19.3	12.2 14	22.5 34	19.5 39	5.6 8	8.1 13	8.8 31	4.6 16	5.9 24	3.6 8	1.5 8	3.5 15	3.1 25	6.2 17	8.1 12	10.7 10	4 6	7.1 7	6.4 13	21.5 10	20.8 7	16.3 3	22.5 15	24.4 10	27.8 25
Graph-based sparse matting	16	16.6	16.6	14.8	12.6 20	20.5 26	14.8 16	5.7 12	7.3 7	6.4 4	4.5 14	5.3 15	3.7 10	1.4 7	3.3 13	2.3 9	6.3 19	7.9 8	11.1 12	4.2 9	8.3 15	6.4 12	28.7 34	31.3 35	27.1 31	23.6 18	25.1 14	27.3 24
Patch-based Matting	16.1	10.8	17.8	19.8	10.9 6	19 19	15.7 22	6 15	9.5 27	8.3 23	4.3 10	5.2 12	4.2 22	1.6 10	3.2 10	2.6 13	5.2 2	9 19	12.4 18	4.7 15	9.7 22	7 18	21.6 11	21.7 8	24.9 24	23.5 17	28.1 25	25.6 18
KL-Divergence Based Sparse Sampling	16.7	15.8	15.8	18.5	11.6 11	17.5 13	14.7 13	5.6 9	8.5 18	8 16	4.9 31	5.3 13	3.7 11	1.5 9	3.5 14	2.1 5	5.8 9	8.3 13	14.1 29	5.6 26	9.3 20	8 26	24.6 22	27.7 29	28.9 34	20.7 9	22.7 6	23.9 14
TSPS-RV Matting	17.6	16.3	16.8	19.9	11.3 10	16.4 11	13.7 6	6.1 16	8.1 15	8.6 28	4.5 12	5.4 17	4.1 19	1.4 6	3.3 11	3.5 35	7.9 34	8.9 17	12.4 20	6.2 30	9 18	8.7 32	22.8 14	23.5 18	21.4 16	20.7 8	28.5 27	22.2 3
Iterative Transductive Matting	18.5	19.9	18.1	17.5	13.1 25	17.2 12	15.6 21	5.7 11	8.6 20	7.8 13	5.1 34	5.5 18	3.9 12	1.9 18	5.8 31	2.6 14	6.6 22	8.5 15	13.8 28	5.4 20	10 23	7.4 23	25.5 24	24 19	23.8 21	20.1 5	22.7 7	22.7 8
Comprehensive sampling	18.6	16	18.5	21.4	11.2 9	18.5 17	14.8 14	6.5 24	9.5 26	8.9 33	4.5 13	4.9 9	4.1 18	1.7 13	3.1 9	2.3 11	5.4 5	9.8 23	13.4 26	5.5 24	11.5 30	7.4 25	23.9 19	22 10	22.8 18	23.8 21	28 24	28.1 26
SVR Matting	18.8	21.6	18.6	16	18.7 43	30.7 45	19.1 36	6.8 30	7.7 12	7.6 12	4.7 25	5 11	3.4 5	1.9 19	4.7 23	2.9 19	5.8 8	8.7 16	10.5 7	4.3 11	8 13	5.6 10	21.2 8	22.1 11	17.1 5	25.6 29	26.1 18	30.6 34
Comprehensive Weighted Color and Texture	19.1	19.3	19.8	18.3	14.6 32	16 9	15.7 23	6.8 29	10 30	7.9 15	4.3 9	5 10	4.1 16	1.7 12	3.5 16	2.2 6	5.4 4	9.9 25	12.8 24	4.3 12	7.4 8	5.2 6	28.3 33	28.1 30	25.4 27	24 23	30.2 30	28.7 29
Sparse coded matting	19.6	23.1	20.4	15.4	13.7 29	25.8 41	14.8 17	6.4 21	8.2 16	6.2 2	4.7 20	5.4 16	4 14	1.8 16	3.1 8	2.3 8	5.9 12	8 11	10.6 8	4.5 13	8 11	5.5 9	30.3 37	33.1 39	29.2 35	27.7 37	27.2 21	29 30
LocalSamplingAndKnnClassification	21.1	23.8	18.9	20.6	12.6 19	16 10	12.4 3	5.8 13	8.1 14	8 17	4.5 15	5.5 20	4.1 15	2.2 28	5.1 26	3.4 33	8.1 35	10.5 27	15.6 34	7.3 34	12.3 33	9.4 33	24.1 20	21.8 9	19.7 10	24.7 26	24.8 12	25.9 20
Weighted Color and Texture Matting	21.6	19.4	23.5	21.9	13.1 26	17.8 15	15.8 24	6.5 23	9.4 24	8.6 27	4.2 8	4.7 7	3.9 13	1.7 15	6 32	2.7 15	6.4 20	11 30	16.3 35	4.8 16	9.1 19	6.5 14	23.7 16	24.8 21	23.2 19	26.5 31	40.2 40	28.5 28
CCM	21.9	25.1	21.6	18.9	13.8 30	20.8 27	16.9 32	6.4 22	8.9 22	8.2 22	4.7 21	5.9 25	3.6 7	2.5 32	4.3 20	3 20	7 26	9 18	10.6 9	4.9 17	8.1 14	5.7 11	25.6 25	27.5 28	24.5 23	25.4 28	26.4 19	28.2 27
Shared Matting	22.4	20.6	26	20.5	10.8 5	20.5 25	15 18	7.8 36	11.6 37	8.1 18	4.2 7	5.3 14	4.2 21	2.1 21	5.8 30	2.9 18	5.9 14	9.2 20	11.4 14	5 18	8.8 16	6.8 16	34.9 42	34.9 40	34.3 40	23.9 22	28.4 26	25.7 19
LNCLM matting	22.5	25	22.1	20.3	10.9 7	11.2 4	16.7 30	6.9 32	8.9 23	7.2 7	5.6 40	7 41	4.1 17	2.5 34	5.1 27	3.5 36	7.5 29	10 26	12 17	5.5 25	11.3 27	7.3 22	25.2 23	23 16	19.9 12	21.2 10	25 13	26.4 21
PDMS	24	23.5	24.8	23.6	12.9 24	19.3 20	14.6 11	6.2 19	10.2 32	8.5 25	4.8 29	6.1 28	4.2 24	2.1 23	4.4 21	3.1 24	5.3 3	8.3 14	11.7 15	5.5 22	11 26	7.1 21	29.6 35	32.2 37	31.6 38	26.8 33	27.1 20	29.1 31
Global Sampling Matting	25.1	21.8	27.6	26	10.9 8	22.7 35	15.4 19	6.3 20	9.5 28	9 34	4.7 22	6.4 35	4.3 28	2.2 29	5.6 29	3.4 32	6.9 25	9.6 22	12.9 25	6.3 31	12.5 34	8.6 31	25.8 26	27.5 27	25.3 26	22 13	24.4 11	23.7 13
Segmentation-based matting	26	26.9	25	26.3	12.8 23	23.5 37	16.6 29	6.6 25	8.3 17	7.3 10	4.8 30	6.1 29	4.3 29	2.1 22	3.9 18	3.1 23	6.7 23	8 9	13.4 27	6 29	8.8 17	8.2 27	31.6 38	35.6 41	38.8 42	24.5 25	32 32	26.7 23
SRLO Matting	26	24.9	28	25.3	14.7 33	18 16	17.7 34	6.9 31	10.7 33	8.9 32	4.9 32	5.7 22	4.7 36	2.1 24	6.5 33	2.8 17	6.3 18	10.9 29	15.2 33	5.4 19	11.6 31	7 20	26.5 31	29.7 32	25.1 25	21.7 11	28.5 28	22.3 5
Improved color matting	27.2	27.3	26.4	27.9	14.9 34	24.5 39	20 40	6.7 27	9.5 25	8.5 26	4.6 17	6.1 30	4.3 30	2.6 36	5.4 28	3.4 34	7.5 30	9.9 24	12.5 22	6 27	10.1 24	8.4 29	26.1 27	26.7 26	23.6 20	23.8 20	25.6 15	26.7 22
Local Spline Regression (LSR)	27.5	29.8	24.1	28.8	12.2 15	20 23	16.2 25	6.1 17	8.8 21	8.1 19	5.2 36	6.2 32	4.6 33	2.2 30	4.9 25	3.1 27	9.4 40	11.9 34	18.3 38	8.2 37	11.4 28	10.1 35	26.4 29	22.5 13	20.2 13	27 34	26 17	39.8 40
KNN Matting	28	30.1	29.4	24.5	16.2 38	19.7 21	16.8 31	8 37	11 34	9 36	4.7 23	6.7 38	4.3 25	3 39	7.7 39	3.7 37	9.2 38	11.3 32	11.3 13	6 28	10.4 25	6.7 15	18.1 3	19.6 5	17 4	27.4 35	41 41	32.7 35
Global Sampling Matting (filter version)	28.1	26	30.4	28	12.3 17	24.3 38	16.3 26	7.3 34	10.2 31	9.5 37	5.1 35	6.4 34	4.7 37	2.4 31	4.7 24	3.2 29	5.9 10	9.5 21	12.4 19	6.5 32	13.1 35	8.3 28	26.5 30	28.3 31	30 37	23.6 19	29.1 29	23.5 11
Learning Based Matting	28.8	29.4	27.9	29.3	16 37	22 33	18.7 35	6.6 26	7.4 9	7.4 11	4.8 27	6.1 27	4.3 31	2.1 20	3.7 17	2.8 16	7.5 31	14.5 40	19.5 41	8.6 41	14.1 38	14.6 43	22.5 12	24.8 20	19.9 11	34.6 41	38.5 39	51.2 46
LMSPIR	30.1	29.1	31.6	29.6	15.2 36	20 22	19.1 37	6.7 28	11.2 35	8.7 30	4.8 28	5.8 23	4.6 35	2.1 25	6.8 36	3 22	7.9 33	14.3 39	20.2 42	5.5 23	11.4 29	7 19	29.7 36	31 34	29.6 36	24 24	34.2 35	25 16
Shared Matting (Real Time)	30.4	29	31.3	31	12.4 18	21.6 29	16.3 27	9.5 40	13.5 39	9.9 38	4.4 11	5.6 21	4.4 32	2.5 35	6.8 37	3.2 30	7.1 27	10.8 28	12.6 23	5.4 21	9.7 21	7.4 24	35.5 44	35.8 42	35.5 41	27.6 36	33.4 33	29.8 33
Closed-Form Matting	30.9	29.4	28.5	34.8	12.7 21	21.9 32	17.2 33	5.9 14	8.5 19	8.6 29	4.7 24	6 26	4.3 27	2.2 26	4.6 22	3.3 31	9.3 39	12.1 35	19.3 40	8.3 38	14.9 40	13.4 42	34.2 41	32.4 38	27.4 32	26.5 32	25.7 16	48.3 44
Improving Sampling Criterion	34.9	33.9	36.5	34.4	12.7 22	21.1 28	16.4 28	11.5 43	17 44	12.1 43	5.8 42	8.1 44	5.7 42	5.4 47	12.1 46	6.6 46	9.6 42	15.7 41	17.8 36	10.2 43	17 41	11.2 40	23.8 18	26.7 25	25.9 28	22.2 14	27.3 23	23.7 12
Cell-based matting Laplacian	35.1	37.3	33.9	34.3	15.1 35	21.7 30	15.6 20	7.6 35	11.4 36	9 35	5.7 41	6.7 39	5.2 40	3.1 40	6.7 34	4.5 40	8.6 36	11.4 33	14.9 31	8.5 40	13.5 37	11.1 38	27.7 32	26.2 24	27.6 33	32.4 39	37.6 38	37.9 37
Large Kernel Matting	35.3	37.1	34.6	34.3	17.2 39	21.8 31	20.7 41	7.2 33	9.6 29	8.4 24	5.3 37	6.6 37	4.6 34	2.9 38	8.2 41	4.2 38	8.6 37	12.1 36	14.7 30	8 36	13.4 36	11.2 39	33 39	31.8 36	26.1 29	32.1 38	32 31	38.4 39
Robust Matting	36.1	32.3	37	39	17.3 40	28.4 43	21.1 42	10.1 41	16.9 43	11.4 41	4.8 26	6.5 36	5 39	2.8 37	7.3 38	4.4 39	7.3 28	14 38	18.1 37	6.8 33	14.6 39	10.6 37	22.7 13	26.1 23	32.1 39	34.4 40	37 36	38 38
SPS matting	38.1	37.5	41.1	35.8	13.4 27	23 36	14.8 15	12.5 44	18.5 45	12.4 44	6.6 46	9.4 47	6.5 47	4.5 45	12.7 47	5.4 43	9.5 41	16.4 43	18.6 39	9.8 42	18.1 44	10.6 36	26.1 28	30.9 33	26.2 30	25 27	33.5 34	29.5 32
High-res matting	39.2	37.8	40.5	39.4	18.6 42	25.8 40	24.6 44	8.6 38	14.1 40	11.1 40	5 33	6.2 31	4.8 38	2.5 33	8.3 42	3.2 28	7.8 32	14 37	21.4 43	8.5 39	18.1 45	12.2 41	35.3 43	38.1 44	42.6 45	38.7 42	54.6 45	36.8 36
Transfusive Weights	39.6	39.5	39.4	40	23.2 44	26.7 42	22.4 43	9.2 39	11.9 38	10.4 39	6.1 44	8.1 43	5.9 44	3.8 43	8 40	5.3 42	12.9 45	21.4 45	37.6 49	13.1 48	22.8 47	18.3 48	20.9 7	22.9 14	19 8	59.5 46	65.7 46	72.8 47
Random Walk Matting	42.9	44.5	40.5	43.8	17.9 41	20.3 24	19.4 38	11.3 42	15.6 41	11.8 42	5.8 43	7 40	6.3 46	3.4 41	6.7 35	4.6 41	13.1 47	22.1 46	27.4 45	12.3 47	18 43	15.7 46	44.1 48	43.5 47	41 44	75.1 47	81.8 48	80.6 48
Geodesic Matting	44.1	45	43.9	43.5	26.9 47	38.5 48	32.5 47	14.2 45	16.5 42	17.4 46	11.7 49	14 50	9.4 49	7.6 49	15.1 48	8.7 49	12.8 44	16.7 44	15.1 32	7.3 35	12.1 32	9.8 34	37.3 46	37.4 43	42.8 46	48.6 45	50 44	48.6 45
Iterative BP Matting	45.2	44.5	45.1	46	23.6 45	29.9 44	27.2 45	16.7 46	24.3 47	20.7 49	6.7 47	9 45	6.3 45	3.8 42	11.3 44	6.8 48	14.1 48	22.8 47	27.9 46	11.4 45	19 46	14.7 44	33.4 40	39.3 45	47.5 49	40.6 43	48.1 43	45.1 42
Easy Matting	45.6	46	45	45.9	23.9 46	32.6 46	30 46	17.1 47	21.8 46	19.4 48	6.3 45	7.5 42	5.8 43	4.7 46	10.5 43	5.6 44	12.1 43	15.7 42	22.9 44	11.2 44	17 42	14.8 45	49.5 49	49.6 49	46.2 48	77.8 48	108.6 50	109.2 49
Improved Bayesian	46.1	46	46.5	45.9	31.2 49	34.9 47	33.9 49	17.8 48	24.4 48	17.2 45	5.5 39	9.3 46	5.3 41	3.9 44	11.4 45	6.6 47	13 46	29.5 48	34.6 48	11.9 46	24.5 48	16.1 47	42.9 47	44.6 48	46 47	92.4 49	46.5 42	45.4 43
Bayesian Matting	47.4	47.5	48.4	46.3	30.3 48	42.4 49	33.4 48	19.2 49	25.8 49	18.4 47	10.8 48	12.4 48	10.8 50	6.6 48	18.5 50	6.2 45	14.2 49	29.8 49	33.2 47	15.4 49	30.6 49	19.7 49	35.8 45	40.6 46	39.6 43	45.3 44	76.8 47	43.6 41
Poisson Matting	49.8	50	49.6	49.8	51.8 50	56.2 50	52 50	28.3 50	43.5 50	30.7 50	12.1 50	13.7 49	9.2 48	11.7 50	18.4 49	11.2 50	22.4 50	36.8 50	55.5 50	21.4 50	32.2 50	22.7 50	53.6 50	72.9 50	58.4 50	125.5 50	84.8 49	139.7 50

Troll - Input image
Drag the window to change the zoom.

References

Method	Reference and notes	Implementation details
Closed-Form Matting	A. Levin, D. Lischinski, Y. Weiss, A Closed Form Solution to Natural Image Matting, CVPR, 2006	Matlab implementation on a Intel Core2 Quad with 2.4 GHZ
Bayesian Matting	Y.Y. Chuang, B. Curless, D. Salesin, R. Szeliski, A Bayesian Approach to Digital Matting, CVPR, 2001	C++ implementation on a Intel Core2 Quad with 2.4 GHZ
Poisson Matting	J. Sun, J. Jia, C.K. Tang, H.Y. Shum, Poisson matting, SIGGRAPH, 2004	Matlab implementation on a Intel Core2 Quad with 2.4 GHZ
Easy Matting	Y. Guan, W. Cheny, X. Liang, Z. Ding, Q. Peng, Easy Matting: A Stroke Based Approach for Continuous Image Matting, Eurographics, 2006	C++ implementation on a Intel Core2 Quad with 2.4 GHZ
Random Walk Matting	L. Grady, T. Schiwietz, S. Aharon, Random Walks For Interactive Alpha-Matting, VIIP, 2005	Matlab/C++ implementation on a Intel Core2 Quad with 2.4 GHZ
Robust Matting	J. Wang, M. Cohen, Optimized Color Sampling for Robust Matting, CVPR, 2007	C++ implementation on a Intel Core2 Quad with 2.4 GHZ
Geodesic Matting	Xue Bai, Guillermo Sapiro, A geodesic framework for fast interactive image and video segmentation and matting, ICCV 2007	C++ implementation on a Intel Core2 Duo with 2.53 GHZ
Iterative BP Matting	Jue 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 matting	C. Rhemann, C. Rother, M. Gelautz, Improving Color Modeling for Alpha Matting. BMVC, 2008	Matlab implementation on a Intel Core2 Duo with 2.4 GHZ
High-res matting	C. Rhemann, C. Rother, A. Rav-Acha, M. Gelautz, T. Sharp, High ResolutionMatting via Interactive Trimap Segmentation. CVPR, 2008	Matlab/C++ implementation on a Intel Core2 Duo with 2.4 GHZ
Large Kernel Matting	Kaiming He, Jian Sun, and Xiaoou Tang, Fast Matting using Large Kernel Matting Laplacian Matrices, CVPR 2010	C++ implementation on a Intel Core Duo with 2 GHZ
Segmentation-based matting	Christoph Rhemann, Carsten Rother, Pushmeet Kohli, Margrit Gelautz, A Spatially Varying PSF-based Prior for Alpha Matting, CVPR 2010	Matlab/C++ implementation on a Intel Core2 Quad with 2.39 GHZ
Shared Matting	Eduardo S. L. Gastal and Manuel M. Oliveira, Shared Sampling for Real-Time Alpha Matting, Eurographics, 2010	C++/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, 2010	C++/GLSL implementation on a Core 2 Quad with 2.8 GHZ
Learning Based Matting	Yuanjie Zheng, Chandra Kambhamettu, Yuanjie Zheng, Chandra Kambhamettu. Learning Based Digital Matting. ICCV 2009. SOURE CODE	Matlab/C++ implementation on a Intel Core2 Duo with 2.53 GHZ
LMSPIR	Bei He, Guijin Wang, Zhiwei Ruan, Xuanwu Yin, Xiaokang Pei, Xinggang Lin, Local Matting based on Sample-pair Propagation and Iterative Refinement, ICIP 2012	C++ implementation on a Intel Core2 Dual with 2 GHZ
SVR Matting	Zhanpeng Zhang, Qingsong Zhu, Yaoqin Xie, Learning Based Alpha Matting using Support Vector Regression, ICIP 2012	Matlab implementation on a Intel Pentium Dual-Core with 3 GHZ
Cell-based matting Laplacian	Chen-Yu Tseng and Sheng-Jyh Wang, A cell-based matting Laplacian for contrast enhancement, ICIP 2012	C++ implementation on a Intel Core i3 with 3 GHZ
Global Sampling Matting	Kaiming He, Christoph Rhemann, Carsten Rother, Xiaoou Tang, and Jian Sun, A Global Sampling Method for Alpha Matting, CVPR 2011	C++ 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, 2010	C++ implementation on a Intel Core2 with 3 GHZ
Weighted Color and Texture Matting	E.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 Matting	Qifeng Chen, Dingzeyu Li, Chi-Keung Tang, KNN Matting, CVPR 2012	Matlab implementation on a Intel Core 2 Duo with 2.13 GHZ
SRLO Matting	Bei 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, 2013	C++ implementation on a Intel Core2 Dual with 2 GHZ
LNSP Matting	Xiaowu Chen, Dongqing Zou, Ping Tan, Image Matting with Local and Nonlocal Smooth Priors, CVPR 2013	matlab implementation on a intel core2 with 2.2 GHZ
CCM	Yongfang 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 Matting	Bei He, Guijin Wang, Chenbo Shi, Xuanwu Yin, Bo Liu, Xinggang Lin, Iterative Transductive Matting, ICIP 2013	Matlab implementation on a Intel Core2 Dual with 2.2 GHZ
Improving Sampling Criterion	Jun Cheng, Zhenjiang Miao, Improving Sampling Criterion for Alpha Matting, RACVPR2013 in Conjunction with ACPR2013	C++ implementation on a Core i5 with 2.5 GHZ
Transfusive Weights	Kaan Yucer, Alexander Sorkine-Hornung, and Olga Sorkine-Hornung, Transfusive Weights for Content-Aware Image Manipulation, VMV2013	Matlab implementation on a Quad-Core Intel Xeon with 3.2 GHZ
Comprehensive sampling	E.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 Texture	E.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 matting	Ahmad 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 Bayesian	Wenshuang Tan, Automatic Matting of Identification Photos, CAD/Graphics, 2013	C++ implementation on a Intel Core(TM)i7-2600 with 3.4 GHZ
Sparse coded matting	Jubin Johnson, Deepu Rajan, Hisham Cholakkal, Sparse Codes as Alpha Mattes, BMVC 2014.	Matlab implementation on a Intel Xeon with 3.2 GHZ
LNCLM matting	B.-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 matting	Jubin 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 Sampling	Levent 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
LocalSamplingAndKnnClassification	Xiao 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 Matting	Donghyeon Cho, Yu-Wing Tai, Inso Kweon, Natural Image Matting using Deep Convolutional Neural Networks. ECCV 2016	matlab implementation on a Intel Core i7 with 3.4 GHZ
CSC Matting	Xiaoxue 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 Matting	Guangying 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 Matting	Ahmad 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 Matting	Ning Xu, Brian Price, Scott Cohen and Thomas Huang, Deep Image Matting, CVPR 2017	Matlab implementation on a I7 with 2.7 GHZ
Information-flow matting	Yagiz Aksoy, Tunc Ozan Aydin and Marc Pollefeys, Designing Effective Inter-Pixel Information Flow for Natural Image Matting, CVPR 2017	Matlab implementation on a Intel Xeon with 3.5 GHZ
ATPM Matting	Xiangyu Zhu, Ping Wang, Zhenghai Huang, Adaptive Propagation Matting Based on Transparency of Image, Multimedia Tools and Applications, 2017 (Online First)	matlab implementation on a Intel Xeon with 2.4 GHZ
Three-layer graph matting	Chao Li, Ping Wang, Xiangyu Zhu, Huali Pi, Three-layer graph framework with the sumD feature for alpha matting. Computer Vision and Image Understanding, vol. 162, pp. 34-45, 2017	c++, octave implementation on a Intel Xeon with 3.2 GHZ
PDMS	Yihui Liang, Pixel-level Discrete Multiobjective Sampling for Alpha Matting, IEEE Transaction on Image Processing, 2017, submitted.	matlab implementation on a Intel i5 2400 with 3.1 GHZ
Three Stages Matting	Xiao Chen, A Three-Stage Matting Method, submitted to MDPI/Applied Sciences, 2017	matlab implementation on a i7 6700k with 4 GHZ
Superpixel-affinity matting	Huali Pi, Submitted to Computer Vision and Image Understanding, 2017	Matlab implementation on a Intel Xeon with 2.4 GHZ
FE2E High-Quality Matting	Anonymous, Learning a Fully End-to-End Convolutional Neural Network for High-Quality Alpha Matting, Anonymous ECCV 2018 submission 382	Matlab/C++ implementation implementation on a Intel(R) Xeon(R) with 2.2 GHZ