yq1011 / colorization-project Goto Github PK
View Code? Open in Web Editor NEWThis project forked from unizard/colorization-project
This project forked from unizard/colorization-project
======================================================================== INTRODUCTION Fully Automatic Image Colorization Code Created by Zezhou Cheng ([email protected]) This MATLAB code implements the colorization algorithm presented in the following paper: Zezhou Cheng, Qingxiong Yang, and Bin Sheng. Image Colorization Using Neural Networks. Submitted to IEEE Transactions on Image Processing 2016. The preliminary version of this work is described in: Zezhou Cheng, Qingxiong Yang, and Bin Sheng. Deep Colorization. Proceedings of the IEEE International Conference on Computer Vision. 2015: 415-423. ======================================================================== INSTALLATION This code was tested on MATLAB 2015b under UBUNTU 14.04.4 LTS If you want to colorize your own images, you need to install the following package: Caffe : https://github.com/longjon/caffe/tree/future OR https://github.com/BVLC/caffe/ Please refer to http://caffe.berkeleyvision.org/installation.html ======================================================================== USAGE (1) For the experiment on your own test images : Single image colorization(default name of image 'test.jpg') : --- run demo_single.m Batch colorization (default path of images 'testset'): --- run demo_batch.m (2) For a quick experiment on the bundled examples without the requirement of installing CAFFE: --- run run_examples.m ======================================================================== LIBRARY The following libraries are included in this code : (1) DAISY Descriptor http://cvlab.epfl.ch/software/daisy (2) GIST Descriptor http://people.csail.mit.edu/torralba/code/spatialenvelope/ (3) Fully Convolutional Networks For semantic Segmantation https://github.com/shelhamer/fcn.berkeleyvision.org Note that we retrained this model on grayscale version of images from SIFT Flow Database. Our trained model is placed in 'scene_parsing_model' folder, named as 'semantic_segmentation.caffemodel' (4) Domain Transform RF filter http://inf.ufrgs.br/~eslgastal/DomainTransform/
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.