Hallucinating face by eigentransformation
By Xiaogang Wang, Xiaoou Tang. IEEE Trans. Syst. Man Cybern. Part C, 2005
480 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Media Technology
View Paper: https://www.semanticscholar.org/paper/791d46aa9cdd40bc9d82067a2e9b71785c62838b
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Dacheng Tao
- Luc Van Gool
- Ming-Hsuan Yang
- Chunhua Shen
- Xiaogang Wang
- Lei Zhang
- Chen Change Loy
- Yi Yang
In Media Technology
- Liangpei Zhang
- Dacheng Tao
- Huanfeng Shen
- Pong Chi Yuen
- Wilman W. W. Zou
- Ce Liu
- Xinbo Gao
- Qiangqiang Yuan
Citations in the corpus
- Wavelet-SRNet: A Wavelet-Based CNN for Multi-scale Face Super Resolution (2017, background): “[29] estimate landmarks and facial pose before reconstructing HR images while the accurate estimation is difficult for rather small faces.”
- Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis (2012, methodology): “This method works well in face hallucination [25].”
- FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors (2017, methodology): “[37] implemented the mapping between LR and HR faces by an eigen transformation.”
- Super-resolution: a comprehensive survey (2014, unknown): “– [189], [190], [213], [298], [299], [322], [323], [338], [339], [349], [433], [453], [469], [480], [510], [537],”
- Face Hallucination: Theory and Practice (2007, background): “To avoid this problem some other researchers tried to only do face hallucination in the interior region of face [42, 9].”
- Hallucinating face by position-patch (2010, methodology): “In order to achieve the optimal results in Wang’s method [9], we used image pairs of 270 people for training and let variance contribution rate of PCA be 0.”
- A Comprehensive Survey to Face Hallucination (2013, methodology): “The idea of eigentransform was then applied to FSR (Wang and Tang 2003, 2005).”
- Image super-resolution: The techniques, applications, and future (2016, background): “SR is also important in biometric recognition, including resolution enhancement for faces [24,201,202], fingerprints [203], and iris images [65,204].”
- Very low resolution face recognition problem (2010, methodology): “Existing learning-based face SR algorithms can be roughly categorized into two approaches, namely examplebased approach [9] [11] [10] [12] [18] and maximum a posterior (MAP) based approach[1] [2] [8].”