Comments (4)
For correct landmarks this should not happen. Maybe check your landmark labels that they correspond with the FLAME landmarks. Once you are sure that everything is correct with the landmarks and you still get extremely distorted shapes, you can choose a higher weight in the code for the different priors (i.e. shape, pose, expression). Increasing these prior weights will regularize the parameters more and therefore constrain the shapes that you will get. Does this help you?
from tf_flame.
@TimoBolkart In fact, in large pose or some cases that is difficult to annotate, there is a gap between the annotated landmarks and the flame-defined landmark, so I think maybe the loss function should be modified to overcome the gap,for example using exponent function instead of l1 when loss is small, so that it will be tolerant for the annotation deviation. I have tried higher weight for priors you mention, which will lead to a more stable result but larger fitted landmark projection distance. The better solution is always adding more constraint like Ringnet.
from tf_flame.
You are absolutely right in cases of wrong or noisy landmarks, one could use some robustifier function before applying the loss, if some keypoints are not well fitted, one could either use a different loss (e.g. some exponential function) or weight some landmarks higher before summing the losses up. Other constraints like multi-person or multi-view information of course can also help to get better results.
from tf_flame.
Did you manage to solve your problem?
from tf_flame.
Related Issues (20)
- AlbedoMM Clipping Textures HOT 11
- About tf2.3.1
- Unlabelled mask region in Flame. HOT 1
- Directly fitting the 3D mesh
- Help with projection Matrix
- ImportError: cannot import name 'plyutils' HOT 2
- windows HOT 3
- texture_data_512.npy missing HOT 1
- How to dump FLAME paramters from fitting results? HOT 1
- where is female_model.pkl? HOT 1
- imgHQ00088_lmks.npy HOT 3
- match shape and expression in TF_FLAME and blender HOT 1
- How to improve Texture Image HOT 4
- Some really honest questions HOT 2
- how to make imgHQ00088_lmks.npy file?
- Jaw articulation parameters HOT 6
- Render checkboard-like texture on flame models HOT 1
- About registration
- FLAME expression base meaning
- How to obtain the texture_data_1024.npy file?
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 tf_flame.