视觉，传感
与智能系统

点击以启动邮件客户端 Mail: info@.balsisvcom
Subject: Asking for Single Image Refocusing and Defocusing data
Body: Your purpose, your mail and your affiliation are needed.
NOTICE: All the data should be only used for research purpose. Please cite the following papers when using these data:

1. Wei Zhang and Wai-Kuen Cham, “Single Image Focus Editing,” in Proceedings of IEEE International Conference on Computer Vision workshop on Color and Reflectance in Imaging and Computer Vision (ICCV-CRICV), Kyoto, Japan, Oct. 2009.
2. Wei Zhang and Wai-Kuen Cham, “Single Image Refocusing and Defocusing,” IEEE Transactions on Image Processing (T-IP)，vol. 21, no. 2, pp. 873-882, 2012.

点击以启动邮件客户端 Mail: info@.balsisvcom
Subject: Asking for Gradient-directed Multi-exposure Composition data
Body: Your purpose, your mail and your affiliation are needed.
NOTICE: All the data should be only used for research purpose. Please cite the following papers when using these data:

1. Wei Zhang and Wai-Kuen Cham, "Gradient-directed Composition of Multi-exposure Images," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
2. Wei Zhang and Wai-Kuen Cham, “Gradient-directed Multi-exposure Composition,” IEEE Transactions on Image Processing (T-IP),21(4):2318-23, Apr. 2012.

点击以启动邮件客户端 Mail: info@.balsisvcom
Subject: Asking for Gradient-directed Multi-exposure Composition software
Body: Your purpose, your mail and your affiliation are needed.
NOTICE: This software is only be used for research purpose. Please cite our papers if you get some publications:

1. Wei Zhang and Wai-Kuen Cham, "Gradient-directed Composition of Multi-exposure Images," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
2. Wei Zhang and Wai-Kuen Cham, “Gradient-directed Multi-exposure Composition,” IEEE Transactions on Image Processing (T-IP),21(4):2318-23, Apr. 2012.
3. Wei Zhang and Wai-Kuen Cham. Reference-guided Exposure Fusion in Dynamic Scenes. Visual Communication and Image Representation (VCIR), vol.23, no.3, pp.467-475, 2012.

点击以启动邮件客户端 Mail: info@.balsisvcom
Subject: Asking for "Hallucinating Face in the DCT Domain" software
Body: Your purpose, your mail and your affiliation are needed.
NOTICE: This software is only be used for research purpose. Please cite our papers if you get some publications:

1. Wei Zhang and Wai-Kuen Cham, Learning-based face hallucination in DCT domain, CVPR, 2008.
2. Wei Zhang and Wai-Kuen Cham, Hallucinating Face in the DCT Domain, IEEE TIP, 2011.

Usage:

1. Run generate_input.m to get synthesized LR image.
2. Run learning.m to infer the missing HR frequency components.
3. Run recon_image.m to produce the HR image by IDCT.

Notes: The 'cluster' files are the training set, you can enrich the training set by collecting more images to make the algorithm more robust.