Comments (5)
It mainly depends on the point detection algorithms. The algorithm I used can't handle well with the eyebrows. I think you can try to replace it with a CNN-based algorithm like this one.
from faceswap.
from faceswap.
Thanks, but i use hack, and set eyebrow coordinates bigger for masks. It turns out what you need, eyebrows are captured. 10.09.2018, 09:54, "Wu Huikai" [email protected]:It mainly depends on the point detection algorithms. The algorithm I used can't handle well with the eyebrows. I think you can try to replace it with a CNN-based algorithm like this one.—You are receiving this because you authored the thread.Reply to this email directly, view it on GitHub, or mute the thread.
Hi, @anoire73
Could you tell me which line in the code you modified to be able to swap eyebrows too? Thanks :)
from faceswap.
from faceswap.
points = np.asarray(face_points_detection(im, bbox)) points[17] = points[17] - np.asarray([[0, 40]]) points[18] = points[18] - np.asarray([[0, 40]]) points[19] = points[19] - np.asarray([[0, 40]]) points[20] = points[20] - np.asarray([[0, 40]]) points[21] = points[21] - np.asarray([[0, 40]]) points[22] = points[22] - np.asarray([[0, 40]]) points[23] = points[23] - np.asarray([[0, 40]]) points[24] = points[24] - np.asarray([[0, 40]]) points[25] = points[25] - np.asarray([[0, 40]]) points[26] = points[26] - np.asarray([[0, 40]]) points[27] = points[27] - np.asarray([[0, 40]]) im_w, im_h = im.shape[:2] left, top = np.min(points, 0) right, bottom = np.max(points, 0) x, y = max(0, left-r), max(0, top-r) w, h = min(right+r, im_h)-x, min(bottom+r, im_w)-y return points - np.asarray([[x, y]]), (x, y, w, h), im[y:y+h, x:x+w]
OK, thank you so much. Cheers 👍
from faceswap.
Related Issues (20)
- Is there any Tutorial Available? Kindly provide link please! HOT 1
- Issue: setup the project. HOT 5
- Can this be used in another project? HOT 1
- Simple face swap HOT 4
- Personal uses? HOT 1
- Future work? HOT 2
- Videos with multiple faces HOT 3
- TypeError: Invalid index type HOT 5
- IndexError: index 185 is out of bounds for axis 0 with size 185 HOT 1
- Asian-celeb dataset download link
- error HOT 2
- swap video error HOT 3
- the swapped face does not scale proportionally when the size of two faces vary HOT 1
- How to use for loop to vist all file? HOT 3
- Documentation HOT 1
- Incompatible with newer versions of NumPy
- Please add LICENSE.txt file otherwise other people cannot use it HOT 1
- FileNotFoundError HOT 1
- Everything is right except the console info, is it necessary? HOT 1
- 只替换部分区域 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from faceswap.