Comments (3)
Hi @ChangY-7 ,
How can we get this detailed normal map?
Most of the identity-generic maps are created based on our training data and span the whole facial UV map. The detail normal map, is a patch of skin-pores that is tilled (repeated) accros the facial UV map. We have picked such a tile that resembles the average in our data.
Is there any ground truth for the skin pores?
If you do not have ground truth data for skin pores, a quick search on "detail normal map" yields some ground truth examples and tutorials for synthetic data.
...added on the identity-specific map for improved rendering
Note that we don't literally add it on the identity specific map, but rather use it in a renderer that supports mid-frequency (generated identity specific)and high-frequency (identity generic) normal maps.
from tbgan.
from tbgan.
Hi @ChangY-7 ,
How can we get this detailed normal map?
Most of the identity-generic maps are created based on our training data and span the whole facial UV map. The detail normal map, is a patch of skin-pores that is tilled (repeated) accros the facial UV map. We have picked such a tile that resembles the average in our data.Is there any ground truth for the skin pores?
If you do not have ground truth data for skin pores, a quick search on "detail normal map" yields some ground truth examples and tutorials for synthetic data....added on the identity-specific map for improved rendering
Note that we don't literally add it on the identity specific map, but rather use it in a renderer that supports mid-frequency (generated identity specific)and high-frequency (identity generic) normal maps.
oh, I see. Thank you again for your detailed reply! (^_^)
from tbgan.
Related Issues (12)
- Question about the normal UVmap? HOT 1
- Question about the outputs of the pre-trained model HOT 1
- IS there a way to turn off discriminator training? HOT 4
- Queries about dataset_tool.py
- Strange outputs of the pre-trained models HOT 1
- Code availability update HOT 9
- Pretrained weights HOT 1
- test error HOT 16
- About training strategy HOT 1
- Request for the code to cylindrically unwrap the mean face HOT 2
- Input vectors for the results on the paper 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 tbgan.