wenhua111 Goto Github PK

caffe

Caffe: a fast open framework for deep learning.

crab

deep-learning-experiments

Solutions to Standford's deep learning tutorial

deep-residual-networks

Deep Residual Learning for Image Recognition

detectionandcorrectionnoiseimage

В проделанной работе представлены алгоритмы детектирования импульсного шума на цветных изображениях: morphological detection noise MDN сокращенный вариант morphological filter полный вариант morphological filter fast averaging peer group filter adaptive rank weighted switching filter Алгоритмы исправления импульсного шума на цветных изображениях: median filter switching median filter vector median filter switching vector median filter averaging filter switching averaging filter random filter switching random filter Алгоритмы искусственного зашумления цветных изображений Алгоритм определения типа импульсного шума на цветных изображений

exemplar-cnn

Discriminative Unsupervised Feature Learning with Convolutional Neural Networks

frinrm

Fuzzy Random Impulse Noise Reduction Method (FRINRM)

image-denoising-state-of-the-art

implementation-of-dtbdm-decision-tree-based-de-noising-method-on-max-10-nios-ii-embedded-evaluation

This project is aimed at implementation of a decision-tree-based impulse noise detector to detect the noisy pixels, and an edge-preserving filter to reconstruct the intensity values of noisy pixels (”ieeexplore.ieee.org/iel5/12/6471716/06122015.pdf”) on Max10 soc .

keras-retinanet

Keras implementation of RetinaNet object detection.

mixed-noise-cnn

Codes for Mixed Noise Denoising using CNN

mtcnn_face_detection_alignment

Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks

noise2noise-pytorch

PyTorch Implementation of Noise2Noise (Lehtinen et al., 2018)

robust-aloha

stargan

PyTorch Implementation of StarGAN - CVPR 2018

toolbox

Piotr's Image & Video Matlab Toolbox

vid2vid

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.