jihoonerd / Conditional-Motion-In-Betweening

🕹️ Official Implementation of Conditional Motion In-betweening (CMIB) 🏃

https://jihoonerd.github.io/Conditional-Motion-In-Betweening/

jihoonerd/Conditional-Motion-In-Betweening Issues

About other datasets
Updated 3 months ago
How to use the generated actions in Blender or Unreal?
Closed 2 years ago3
how to conduct the pose-conditioned in-betweening?
Closed 2 years ago2
Question how is the performance in regards to hand/finger movement and facial expressions?
Closed 2 years ago2
hi, how to visualize the result in unity
Closed 2 years ago1
Benchmark models show different l2p,l2q from the paper
Closed 2 years ago4
shaking for start and target when I training my self dataset?
Closed 2 years ago12
where I can find corresponding code about Motion data augmentation?
Closed 2 years ago1
Some questions about the input of network
Closed 2 years ago1
current train.py is not working when cont/disc code dim equal zero
Closed 3 years ago
Experiment with unified labeling code
Closed 3 years ago1
[Major Change] Use BERT-based Transformer Encoder / Transformer Decoder
Closed 3 years ago
Unit length representation in global coordinates
Closed 3 years ago
Current test.py does not support continuous code
Closed 3 years ago1
Use Gumbel-Softmax to handle imbalanced data
Closed 3 years ago
Support 2+ layers in LSTM
Closed 3 years ago
Scheduled L1 Loss
Closed 3 years ago
[Hotfix] Replace label infogan encoder to direct injection
Closed 3 years ago
Root position visualizer
Closed 3 years ago
hyper parameters add to argment in train.py
Closed 3 years ago
Employ long-sighted but not LSTM discriminator
Closed 3 years ago
Test with continuous infogan code
Closed 3 years ago
apply new structure to test.py
Closed 3 years ago
Apply weights & biases, amp(automatic mixed precision)
Closed 3 years ago
Use linear probed discriminator
Closed 3 years ago2
Conditioning inside LSTM, not concatenating whole inputs
Closed 3 years ago
Add teacher forcing
Closed 3 years ago