yanchb3's repositories
awesome-Face_Recognition
papers about Face Detection; Face Alignment; Face Recognition && Face Identification && Face Verification && Face Representation; Face Reconstruction; Face Tracking; Face Super-Resolution && Face Deblurring; Face Generation && Face Synthesis; Face Transfer; Face Anti-Spoofing; Face Retrieval;
CAGFace
Component Attention Guided Face Super-Resolution Network: CAGFace
Progressive-Face-Super-Resolution
Official Pytorch Implementation of Progressive Face Super-Resolution (BMVC 2019 Accepted)
image-super-resolution
🔎 Super-scale your images and run experiments with Residual Dense and Adversarial Networks.
Deep-Convolution-Network-for-Direction-of-Arrival-Estimation-with-Sparse-Prior
this code is for the paper 'Deep Convolution Network for Direction of Arrival Estimation with Sparse Prior' pubished in IEEE spl
Single-Image-Super-Resolution
A collection of high-impact and state-of-the-art SR methods
Stacked-GAN-Face-SR
Stacked GAN face super resolution
AdvDefense_CSC
Code for "Adversarial Defense by Stratified Convolutional Sparse Coding"
GWAInet
Exemplar Guided Face Image Super-Resolution without Facial Landmarks
OCSC
Code for 'Online convolutional sparse coding'.
PWLS-CSCGR
Convolutional Sparse Coding for Compressed Sensing CT Reconstruction
WaveletSRNet
A pytorch implementation of Paper "Wavelet-srnet: A wavelet-based cnn for multi-scale face super resolution"
TA_FrontEnd
The front-end of my final tasks : Single Image Super Resolution for Face Images using Generative Adversarial Network
TA_Server
The back-end of my final tasks : Single Image Super Resolution for Face Images using Generative Adversarial Network
MS-CSC-Rain-Streak-Removal
There is a code of ”Video Rain Streak Removal By Multiscale Convolutional Sparse Coding” in. There are several added comparison results in different real videos to further show the superiority of the MS-CSC model.
CCSC_code_ICCV2017
This is the source code repository for the ICCV 2017 paper "Consensus Convolutional Sparse Coding".
FSRNet
Demo code for our CVPR'18 paper "FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors" (SPOTLIGHT Presentation)
FaceAttr
CVPR2018 Face Super-resolution with supplementary Attributes
Super-Resolution-Networks
Using different sr networks to reconstruct small face images
face-recognition
Identify low-resolution video face images; contain main three sections: face detection,low resolution face super resolution; face recognition.
convsparsecoding
Code accompanying the paper M. Sorel, F. Sroubek, "Fast convolutional sparse coding using matrix inversion lemma", Digital Signal Processing, vol. 55, pp.44-51, 2016
Face-Hallucination-For-Video-Surveillance-Graduation-Project-
a novel face hallucination algorithm to synthesize a high-resolution face image from several low-resolution input face images. Face hallucination normally uses twomodels: a global parametricmodel which synthesizes the global face shapes from eigenfaces, and a local parametric model which enhances the local high frequency details.We follow a similar process to develop a robust face hallucination algorithm. First, we obtain eigenfaces from a number of low resolution face images segmented from a video sequence using a face tracking algorithm. Then we compute the difference between an interpolated low-resolution face and a mean face, and use this difference as the query to retrieve an approximate sparse eigenface representation. The eigenfaces are combined using the coefficients obtained from the sparse representation and added into the interpolated low-resolution face. In this way, the global shape of the interpolated low resolution face can be successfully enhanced. Second, we improve the example-based super-resolution method for local high frequency information enhancement. Our proposed algorithm uses the Approximate Nearest Neighbors (ANN) search method to find a number of nearest neighbors for a stack of queries, instead of finding the exact match for each low frequency patch. Median filtering is used to remove the noise from the nearest neighbors in order to enhance the signal. Our proposed algorithm uses a sparse representation and the ANN method to enhance both global face shape and local high frequency information while greatly improving the processing speed, as confirmed empirically.