You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+5-5Lines changed: 5 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -42,37 +42,37 @@ expression and only using the shape as a template for other methods like [VOCA (
42
42
43
43
## Demo
44
44
45
-
RingNet requires a loose crop of the face in the image.
45
+
RingNet requires a loose crop of the face in the image. We provide two sample images in the **input_images** folder which are taken from [CelebA Dataset](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html).
46
46
47
47
#### Output predicted mesh rendering
48
48
49
49
Run the following command from the terminal to check the predictions of RingNet
It will save a *.npy file of the predicted flame and camera parameters and in **./RingNet_output/params/**.
70
70
71
71
#### Generate VOCA templates
72
72
73
73
If you want to play with the 3D mesh, i.e. neutralize pose and expression of the 3D mesh to use it as a template in [VOCA (Voice Operated Character Animation)](https://github.com/TimoBolkart/voca), run the following command
0 commit comments