Comments (2)
@AIMads Thank you for your interest in this work.
TL;DR
No, the model in this repo does not support that fine details, such as hands or facial expressions.
Limitations
I think the fine-detailed control is more of a data set limitation rather than methods per se. Considering the high quality motion data is mostly retrieved from mocap device, it is still difficult to collect finger or facial muscles. (I think facial muscle data will be far more difficult to get ;) ) However, I think SMPL-X model would be a option if you need to work on detailed motion information. SMPL-X is an extension of SMPL, which only has major joints similar like the kinematic chain in this work. SMPL-H includes finger data on top of the SMPL, and SMPL-X includes facial movements on top of the SMPL-H. But, still I am not sure if there are enough high-quality SMPL-X dataset. As far as I know, the biggest dataset of SMPL-based model is AMASS, but it contains SMPL-H at most.
from conditional-motion-in-betweening.
Thank you so much for the great answer! Alright very interesting will look into SMPL-X ;)
from conditional-motion-in-betweening.
Related Issues (20)
- Use Gumbel-Softmax to handle imbalanced data
- apply new structure to test.py
- hyper parameters add to argment in train.py
- Current test.py does not support continuous code HOT 1
- current train.py is not working when cont/disc code dim equal zero
- Scheduled L1 Loss
- Root position visualizer
- [Hotfix] Replace label infogan encoder to direct injection
- [Major Change] Use BERT-based Transformer Encoder / Transformer Decoder
- Unit length representation in global coordinates
- Experiment with unified labeling code HOT 1
- shaking for start and target when I training my self dataset? HOT 12
- Some questions about the input of network HOT 1
- where I can find corresponding code about Motion data augmentation? HOT 1
- Benchmark models show different l2p,l2q from the paper HOT 4
- hi, how to visualize the result in unity HOT 1
- How to use the generated actions in Blender or Unreal? HOT 3
- how to conduct the pose-conditioned in-betweening? HOT 2
- About other datasets
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 conditional-motion-in-betweening.