Skip to content

Commit c2b1ef3

Browse files
thaoshibethaoshibe
committed
fix readme.md - typos
1 parent f159206 commit c2b1ef3

File tree

3 files changed

+17
-18
lines changed

3 files changed

+17
-18
lines changed

‎Color/README.md

+3-3
Original file line numberDiff line numberDiff line change
@@ -2,12 +2,12 @@
22

33
| ![color-makeup.png](../imgs/color-makeup.png) |
44
|:--:|
5-
| This is training guideline for Color Branch (C), one out of two branches in [Color-Pattern Makeup Transfer (CPM)](../README.md).|
5+
| This is a training guideline for Color Branch (C), one out of two branches in [Color-Pattern Makeup Transfer (CPM)](../README.md).|
66

77
---
88

99
For Color Branch, we used the same CycleGAN-based model like [BeautyGAN](liusi-group.com/pdf/BeautyGAN-camera-ready_2.pdf).
10-
But instead of normal training pair, we used our **novel uv-space**.
10+
But instead of normal training pair, we used our **novel UV-space**.
1111

1212
1. **Download [Makeup Transfer Dataset](http://liusi-group.com/projects/BeautyGAN)** & unzip it. The dataset folder should be like:
1313

@@ -34,4 +34,4 @@ Result will be saved in `--savedir` folder. You should find image pair like this
3434
|:--:|
3535
| From left to right: Segmentation Mask, UV-texture.|
3636

37-
3. **Train Color Branch**: Follow instruction at [BeautyGAN-pytorch-reimplementation](https://github.com/thaoshibe/BeautyGAN-PyTorch-reimplementation) to re-train model with newly established dataset.
37+
3. **Train Color Branch**: Follow instruction at [BeautyGAN-pytorch-reimplementation](https://github.com/thaoshibe/BeautyGAN-PyTorch-reimplementation) or [BeautyGAN-pytorch-implementation](https://github.com/wtjiang98/BeautyGAN_pytorch) to re-train model with newly established dataset.

‎Pattern/README.md

+1-3
Original file line numberDiff line numberDiff line change
@@ -2,9 +2,7 @@
22

33
| ![pattern_segmentation.png](../imgs/pattern_segmentation.png) |
44
|:--:|
5-
| Pattern Makeup | Pattern Segmentation Model|
6-
7-
This is training guideline for Pattern Branch (P), one out of two branches in [Color-Pattern Makeup Transfer (CPM)](../README.md).
5+
| This is a training guideline for Pattern Branch (P), one out of two branches in [Color-Pattern Makeup Transfer (CPM)](../README.md)|
86

97
---
108

‎README.md

+13-12
Original file line numberDiff line numberDiff line change
@@ -11,13 +11,14 @@
1111

1212
- CPM is a holistic makeup transfer framework that outperforms previous state-of-the-art models on both light and extreme makeup styles.
1313
- CPM consists of an improved color transfer branch (based on [BeautyGAN](http://www.colalab.org/projects/BeautyGAN)) and a novel pattern transfer branch.
14-
- The datasets used to train and evaluate CPM contains both real and synthetic, light and extreme examples.
14+
- We also introduce 4 new datasets (both real and synthesis) to train and evaluate CPM.
15+
1516

1617
| ![teaser.png](./imgs/teaser.png) |
1718
|:--:|
1819
| *CPM can replicate **both colors and patterns** from a reference makeup style to another image.*|
1920

20-
Details of the dataset construction, model architecture and experimental results can be found in [our following paper](https://arxiv.org/abs/2104.01867):
21+
Details of the dataset construction, model architecture, and experimental results can be found in [our following paper](https://arxiv.org/abs/2104.01867):
2122

2223
```
2324
@inproceedings{m_Nguyen-etal-CVPR21,
@@ -27,7 +28,7 @@ Details of the dataset construction, model architecture and experimental results
2728
  booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition (CVPR)}
2829
}
2930
```
30-
**Please CITE** our paper whenever our dataset or model implementation is used to help produce published results or incorporated into other software.
31+
**Please CITE** our paper whenever our datasets or model implementation is used to help produce published results or incorporated into other software.
3132

3233
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1K9QVSHPJ8fx9X8yg6KnhE40PPlyW5iNp?usp=sharing) - [![arXiv](https://img.shields.io/badge/arXiv-2104.01867-red.svg)](https://arxiv.org/abs/2104.01867) - [![project page](https://img.shields.io/badge/ProjectPage-up-green.svg)](https://thaoshibe.github.io/CPM)
3334

@@ -37,21 +38,21 @@ Details of the dataset construction, model architecture and experimental results
3738

3839
We introduce ✨ 4 new datasets: **CPM-Real**, **CPM-Synt-1**, **CPM-Synt-2**, and **Stickers** datasets. Besides, we also use published [LADN's Dataset](https://georgegu1997.github.io/LADN-project-page/) & [Makeup Transfer Dataset](http://liusi-group.com/projects/BeautyGAN).
3940

40-
CPM-Real and Stickers are crawled from Google Image Search, while CPM-Synt-1 & 2 are build on [Makeup Transfer](http://liusi-group.com/projects/BeautyGAN) and Stickers. *(Click on dataset name to download)*
41+
CPM-Real and Stickers are crawled from Google Image Search, while CPM-Synt-1 & 2 are built on [Makeup Transfer](http://liusi-group.com/projects/BeautyGAN) and Stickers. *(Click on dataset name to download)*
4142

4243
| Name | #imgs | Description | - |
4344
|:-------------------------------:|:-----:|:-----------------------------------|:----------------------------------:|
4445
|[CPM-Real](https://public.vinai.io/CPM-datasets/CPM-Real.zip)| 3895 | real - makeup styles |![CPM-Real.png](./imgs/CPM-Real.png)|
45-
|[CPM-Synt-1](https://public.vinai.io/CPM-datasets/CPM-Synt-1.zip)| 5555| synthesis - makeup img with pattern segmentation mask|![./imgs/CPM-Synt-1.png](./imgs/CPM-Synt-1.png)|
46+
|[CPM-Synt-1](https://public.vinai.io/CPM-datasets/CPM-Synt-1.zip)| 5555| synthesis - makeup images with pattern segmentation mask|![./imgs/CPM-Synt-1.png](./imgs/CPM-Synt-1.png)|
4647
|[CPM-Synt-2](https://public.vinai.io/CPM-datasets/CPM-Synt-2.zip)| 1625| synthesis - triplets: makeup, non-makeup, ground-truth|![./imgs/CPM-Synt-2.png](./imgs/CPM-Synt-2.png)|
47-
|[Stickers](https://public.vinai.io/CPM-datasets/Stickers.zip)|577| high-quality images with alpha channel, used to create CPM-Synt-1 and CPM-Synt-2 |![Stickers.png](./imgs/Stickers.png)|
48+
|[Stickers](https://public.vinai.io/CPM-datasets/Stickers.zip)|577| high-quality images with alpha channel |![Stickers.png](./imgs/Stickers.png)|
4849

4950
*Dataset Folder Structure can be found [here](https://github.com/VinAIResearch/CPM/blob/main/about-data.md).*
50-
> ***By downloading these dataset, USER agrees:***
51+
> ***By downloading these datasets, USER agrees:***
5152
>
52-
> * to use the dataset for research or educational purposes only
53-
> * to not distribute or part of the dataset in any original or modified form.
54-
> * and to [cite our paper](#cpm-color-pattern-makeup-transfer) whenever the dataset is employed to help produce published results.
53+
> * to use these datasets for research or educational purposes only
54+
> * to not distribute or part of these datasets in any original or modified form.
55+
> * and to [cite our paper](#cpm-color-pattern-makeup-transfer) whenever these datasets are employed to help produce published results.
5556
5657
---
5758

@@ -77,9 +78,9 @@ conda env create -f environment.yml
7778

7879
##### Download pre-trained models
7980

80-
- Download CPM's pretrained models: [color.pth](https://public.vinai.io/CPM_checkpoints/color.pth) and [pattern.pth](https://public.vinai.io/CPM_checkpoints/pattern.pth). Put them in `checkpoints` folder.
81+
- Download CPM’s pre-trained models: [color.pth](https://public.vinai.io/CPM_checkpoints/color.pth) and [pattern.pth](https://public.vinai.io/CPM_checkpoints/pattern.pth). Put them in `checkpoints` folder.
8182

82-
- Download [PRNet pretrained model] from [Drive](https://drive.google.com/file/d/1UoE-XuW1SDLUjZmJPkIZ1MLxvQFgmTFH/view). Put it in `PRNet/net-data`
83+
- Download [PRNet pre-trained model] from [Drive](https://drive.google.com/file/d/1UoE-XuW1SDLUjZmJPkIZ1MLxvQFgmTFH/view). Put it in `PRNet/net-data`
8384

8485
##### Usage
8586

0 commit comments

Comments
 (0)