GitHub - youyuge34/PI-REC: PI-REC: Progressive Image Reconstruction Network With...

README.md

PI-REC

Progressive Image Reconstruction Network With Edge and Color Domain

Paper on arXiv | Paper Read Online | BibTex

When I was a schoolchild,

I dreamed about becoming a painter.

With PI-REC, we realize it nowadays.

For you, for everyone.

English | 中文版

?️‍? Demo show time ?️‍?

Draft2Painting

Tool operation

Introduction

We propose a universal image reconstruction method to represent detailed images purely from binary sparse edge and flat color domain. Here is the open source code and the drawing tool.
*The codes of training for release are no completed yet, also waiting for release license of lab.

Find more details in our paper: Paper on arXiv

Quick Overview of Paper

What can we do?

• Figure (a): Image reconstruction from extreme sparse inputs.
  
• Figure (b): Hand drawn draft translation.
  
• Figure (c): User-defined edge-to-image (E2I) translation.
  

Model Architecture

We strongly recommend you to understand our model architecture before running our drawing tool. Refer to the paper for more details.

Prerequisites

• Python 3+
• PyTorch 1.0 (0.4 is not supported)
• NVIDIA GPU + CUDA cuDNN

Installation

• Clone this repo
• Install PyTorch and dependencies from http://pytorch.org
• Install python requirements:

pip install -r requirements.txt

Usage

We provide two ways in the project:

• Basic command line mode for batch test
• Drawing tool GUI mode for creation

Firstly, follow steps below to prepare pre-trained models with patience:

1. Download the pre-trained models you want here: Google Drive | Baidu (Extraction Code: 9qn1)
2. Unzip the .7z and put it under your dir ./models/.
   So make sure your path now is: ./models/celeba/<xxxxx.pth>
3. Complete the above Prerequisites and Installation

Files are ready now! Read the User Manual for firing operations.

中文版介绍 ?️

Demo演示

自己看上面的咯~

简介

我们提出了一种基于GAN的渐进式训练方法 PI-REC，能从超稀疏二值边缘以及色块中还原重建真实图像。 这属于图像重建，图像翻译，条件图像生成，AI自动绘画的前沿交叉领域，而非简单的以图搜图。更多相关可以阅读论文里的 Related Work。
这里包含了测试代码以及交互式绘画工具。
*由于训练过程过于复杂，用于训练的发布版代码还未完成

在我们的论文中你可以获得更多信息(强烈推荐阅读): Paper on arXiv

论文概览

PI-REC能做啥？

• Figure (a): 超稀疏输入信息重建原图。
  
• Figure (b): 手绘草图转换。
  
• Figure (c): 用户自定义的 edge-to-image (E2I) 转换.
  

模型结构

我们强烈建议你先仔细阅读论文熟悉我们的模型结构，对运行使用大有裨益。

基础环境

• Python 3
• PyTorch 1.0 (0.4 会报错)
• NVIDIA GPU + CUDA cuDNN （当前版本已可选cpu，请修改config.yml中的DEVICE）

第三方库安装

• Clone this repo
• 安装PyTorch和torchvision --> http://pytorch.org
• 安装 python requirements:

pip install -r requirements.txt

运行使用

我们提供以下两种方式运行：

• 基础命令行模式 用来批处理测试整个文件夹的图片
• 绘画GUI工具模式 用来创作

首先，请耐心地按照以下步骤做准备：

1. 在这里下载你想要的预训练模型文件：Google Drive | Baidu (提取码: 9qn1)
2. 解压，放到目录./models下
   现在你的目录应该像这样： ./models/celeba/<xxxxx.pth>
3. 完成上面的基础环境和第三方库安装

啦啦啦啦，准备工作已完成，阅读用户手册来开始运行程序咯~

Acknowledgment

Code structure is modified from Anime-InPainting, which is based on Edge-Connect.

BibTex

@article{you2019pirec,
  title={PI-REC: Progressive Image Reconstruction Network With Edge and Color Domain},
  author={You, Sheng and You, Ning and Pan, Minxue},
  journal={arXiv preprint arXiv:1903.10146},
  year={2019}
}