Algoritmia中文版

不會用ps？不會p照片？不想用美顏相機？那Algoritmia非常適合你，它是由加州大學的一個團隊打造的軟件，Algoritmia能照片變成彩色，更簡單易用的處理照片。

Algoritmia特色說明

Algoritmia自動生成的顏色可能并不是碟子的真實顏色，這時候你就可以在碟子上選取一個點，然后在左側(cè)的編輯框選擇最準確的顏色，Algoritmia就會即刻生成效果圖，你還可以進一步調(diào)整，直到滿意為止。

功能

可手動調(diào)色

可一鍵自動化上色

黑白照變彩色照非常逼真

可將任意黑白照片添加色彩

采用智能色彩識別調(diào)節(jié)技術(shù)

軟件介紹

來自加州大學的Richard Zhang及其團隊推出了一款名為Algoritmia的APP，可以讓黑白照片自動變成彩色，為不少人帶來了福音。然而，Algoritmia也存在一些缺陷，它雖然能把照片變成彩色，但是顏色并不一定準確。該團隊對Algoritmia進行了進一步優(yōu)化，讓用戶可以參與進來，主動來挑選準確的顏色，Algoritmia會根據(jù)用戶的選擇自動調(diào)整，以達到最優(yōu)效果，而這整個過程，比PS要簡單的多。

官方英文簡介

Interactive Deep Colorization

[Project Page] [Paper] [Demo Video] [Seminar Talk]

Richard Zhang*, Jun-Yan Zhu*, Phillip Isola, Xinyang Geng, Angela S. Lin, Tianhe Yu, and Alexei A. Efros. Real-Time User-Guided Image Colorization with Learned Deep Priors. In ACM Transactions on Graphics (SIGGRAPH 2017). (*indicates equal contribution)

We first describe the system (0) Prerequisities and steps for (1) Getting started. We then describe the interactive colorization demo (2) Interactive Colorization (Local Hints Network). There are two demos: (a) a "barebones" version in iPython notebook and (b) the full GUI we used in our paper. We then provide an example of the (3) Global Hints Network.

(0) Prerequisites

Linux or OSX

Caffe

CPU or NVIDIA GPU + CUDA CuDNN.

(1) Getting Started

Clone this repo:

git clone https://github.com/junyanz/interactive-deep-colorization ideepcolorcd ideepcolor

Download the reference model

bash ./models/fetch_models.sh

Install Caffe and Python libraries (OpenCV)

(2) Interactive Colorization (Local Hints Network)

We provide a "barebones" demo in iPython notebook, which does not require QT. We also provide our full GUI demo.

2(a) Barebones Interactive Colorization Demo

Run ipython notebook and click on DemoInteractiveColorization.ipynb.

2(b) Full Demo GUI

Install Qt4 and QDarkStyle. (See [Requirements](## (A) Requirements))

Run the UI: python ideepcolor.py --gpu [GPU_ID]. Arguments are described below:

--win_size    [512] GUI window size --gpu         [0] GPU number --image_file  ['./test_imgs/mortar_pestle.jpg'] path to the image file

User interactions

Adding points: Left-click somewhere on the input pad

Moving points: Left-click and hold on a point on the input pad, drag to desired location, and let go

Changing colors: For currently selected point, choose a recommended color (middle-left) or choose a color on the ab color gamut (top-left)

Removing points: Right-click on a point on the input pad

Changing patch size: Mouse wheel changes the patch size from 1x1 to 9x9

Load image: Click the load image button and choose desired image

Restart: Click on the restart button. All points on the pad will be removed.

Save result: Click on the save button. This will save the resulting colorization in a directory where the image_file was, along with the user input ab values.

Quit: Click on the quit button.

(3) Global Hints Network

We include an example usage of our Global Hints Network, applied to global histogram transfer. We show its usage in an iPython notebook.

Add ./caffe_files to your PYTHONPATH

Run ipython notebook. Click on ./DemoGlobalHistogramTransfer.ipynb

(A) Requirements

Caffe (See Caffe installation document)

OpenCV

sudo apt-get install python-opencv

Qt4

sudo apt-get install python-qt4

QDarkStyle

sudo pip install qdarkstyle

(B) Cat Paper Collection

One of the authors objects to the inclusion of this list, due to an allergy. Another author objects on the basis that cats are silly creatures and this is a serious, scientific paper. However, if you love cats, and love reading cool graphics, vision, and learning papers, please check out the Cat Paper Collection: [Github] [Webpage]