update readme

README.md

@@ -8,15 +8,15 @@
 
 This is an official python implementation of PRN. 
 
-PRN is a method to jointly regress dense alignment and 3D face shape in an end-to-end manner. More examples on Multi-PIE and 300VW can be seen in [YouTube](https://youtu.be/tXTgLSyIha8) 
+PRN is a method to jointly regress dense alignment and 3D face shape in an end-to-end manner. More examples on Multi-PIE and 300VW can be seen in [YouTube](https://youtu.be/tXTgLSyIha8) .
 
 The main features are:
 
 * **End-to-End**  our method can directly regress the 3D facial structure and dense alignment from a single image bypassing 3DMM fitting.
 
 * **Multi-task**  By regressing position map, the 3D geometry along with semantic meaning can be obtained. Thus, we can effortlessly complete the tasks of dense alignment, monocular 3D face reconstruction, etc.
 
-* **Faster than real-time**  The method can run at more than 100fps(with GTX 1080) to regress a position map.
+* **Faster than real-time**  The method can run at over 100fps(with GTX 1080) to regress a position map.
 
 * **Robust** Tested on facial images in unconstrained conditions.  Our method is robust to poses, illuminations and occlusions. 
 
@@ -34,10 +34,12 @@ Dense alignment of both visible and non-visible points(including 68 key points).
 
 * #### 3D Face Reconstruction
 
-Get the 3D vertices and corresponding colours from a single image.  Save the result as mesh data, which can be opened with [Meshlab](http://www.meshlab.net/) or Microsoft [3D Builder](https://developer.microsoft.com/en-us/windows/hardware/3d-print/3d-builder-resources). Notice that, the texture of non-visible area is distorted due to self-occlusion.
+Get the 3D vertices and corresponding colours from a single image.  Save the result as mesh data(.obj), which can be opened with [Meshlab](http://www.meshlab.net/) or Microsoft [3D Builder](https://developer.microsoft.com/en-us/windows/hardware/3d-print/3d-builder-resources). Notice that, the texture of non-visible area is distorted due to self-occlusion.
 
 ![alignment](Docs/images/reconstruct.jpg)
 
+
+
 ### More(To be added)
 
 * #### 3D Pose Estimation
@@ -57,7 +59,7 @@ Get the 3D vertices and corresponding colours from a single image.  Save the res
 
   Optional:
 
-* dlib (for detecting face, you do not have to install if you can provide bounding box information)
+* dlib (for detecting face.  You do not have to install if you can provide bounding box information)
 
 * opencv2 (for extracting textures)
 
@@ -68,20 +70,29 @@ GPU is highly recommended. The run time is ~0.01s with GPU(GeForce GTX 1080) and
 1. Clone the repository
 
 ```bash
-git clone https://github.com/Anonymous7005/PRN.git
-cd PRN
+git clone https://github.com/YadiraF/PRNet
+cd PRNet
 ```
 
 2. Download the PRN trained model at [BaiduDrive](https://pan.baidu.com/s/10vuV7m00OHLcsihaC-Adsw) or [GoogleDrive](https://drive.google.com/file/d/1UoE-XuW1SDLUjZmJPkIZ1MLxvQFgmTFH/view?usp=sharing), and put it into `Data/net-data`
 3. Run the test code.
 
 ```bash
-python test_basics.py
+python run_basics.py #Can run only with python and tensorflow
 ```
 
 
 
+## Contacts
+
+Please contact [Yao Feng]([email protected]) or open an issue for any questions or suggestions(like, push me to add more applications).
+
+Thanks! (*^▽^*)
 
 
 
+## Acknowledgements
 
+- Thanks [BFM team](https://faces.dmi.unibas.ch/bfm/), [Xiangyu Zhu](http://www.cbsr.ia.ac.cn/users/xiangyuzhu/projects/3DDFA/main.htm), and [Anil Bas](https://github.com/anilbas/3DMMasSTN) for sharing 3D data.
+- Thanks Patrik Huber for sharing his work  [eos](https://github.com/patrikhuber/eos), which helps me a lot in studying 3D Face Reconstruction.
+- Thanks the authors of  [3DMMasSTN](https://github.com/anilbas/3DMMasSTN), [DenseReg](https://github.com/ralpguler/DenseReg), [3dmm_cnn](https://github.com/anhttran/3dmm_cnn), [vrn](https://github.com/AaronJackson/vrn), [pix2vertex](Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation), [face-alignment](https://github.com/1adrianb/face-alignment) for making their excellent works publicly available.