wind222's repositories
awesome-rnn
Recurrent Neural Network - A curated list of resources dedicated to RNN
bayesian-video-super-resolution
Bayesian video super-resolution
caffe-lowlevel
Project for paper "Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network", ECCV 2016
Codes-for-Lane-Detection
Codes for the CNN-based lane detection models
coding-interviews
剑指Offer
Convolution-in-RNN
Convolution Neural Network in RNN (GRU、LSTM、etc)
cs231n.github.io
Public facing notes page
DenseNetCaffe
Caffe code for Densely Connected Convolutional Networks (DenseNets)
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.
Face-Hallucination-of-Facial-Components
FH by Neighbor Embedding Facial Components
FudanOCR
A toolbox of scene text detection and recognition
Generative-Adversarial-Network-Demo
Generative Adversarial Network Demo for Fresh Machine Learning #2
generative-adversial
image generation via GANs
LSTM-and-maxlayer-for-SNV-based-phenotype-prediction
Source code used in my MSc thesis "LSTM and convolutional neural networks for SNV-based phenotype prediction Long Short-Term Memory and convolutional neural networks for SNV-based phenotype prediction"
neural-enhance
Super Resolution for images using deep learning.
Photo-Realistic-Super-Resoluton
Torch Implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"
SR-LicensePlate
This is a repository about the paper A.N. Vicente and H. Pedrini: "A Learning-Based Single-Image Super-Resolution Method for Very Low Quality License Plate Images"