This fold contains the source files to reproduce the results presented in our paper "Liquan Shen, Xianqiu Geng, Feifei Li, Ruigang Fang, Yang Yao, Dapeng Wu, A Novel No-Reference Quality Assessment Metric for Stereoscopic Images Using Natural Scene Statistics", submitted. You can change this program as you like and use it anywhere, but please refer to its original source.

1) Please cite the paper (A Novel No-Reference Quality Assessment Metric for Stereoscopic Images Using Natural Scene Statistics)

2) If any question, please contact me through jsslq@163.com.

3) Implementation: 
imdL=imread('iml.bmp');
imdR=imread('imr.bmp');
demo.m

4) Dependencies: 

Folder: BRISQUE_release, svm_temp

MATLAB files: demo.m, disparity_search_ssim.m, cyclopean_image.m, compensated_image.m, estimateaggdparam.m, estimateggdparam.m, ExtractGaborResponse.m, feat_extraction_AGGD_withMSCN.m, feat_extraction_forimagedifference_afterMSCN.m, feat_extraction_GGD.m, feat_extraction_GGD_withMSCN.m, feat_extraction_sub_prod.m, GM_gradientMap.m, log_gabor_filter.m, rmedge.m, shift_image.m, ssim_index.m

Data files: Gabor_no_DC_unit_energy_07_octave.mat

Image Files: iml.bmp, imr.bmp

================================================================================
Note on training: 
This release version  was trained on the entire LIVE 3D Image Quality Database Phase I and Phase II.
