main
Code
is available here: https://github.com/tensorflow/tensor2tensor/blob/master/tensor2tensor/models/video/sv2p.py
Highlights
BAIR robot pushing dataset
Human3.6M dataset
Stochastic Movement Dataset
Stochastic Movement Dataset
Samples in the paper
Samples in the paper
More Samples
More Samples
BAIR Robot Pushing Dataset (action-free)
BAIR Robot Pushing Dataset (action-free)
Yellow frames are context frames while Green frames are predicted frames.
Samples in the paper
Samples in the paper
More samples
More samples
BAIR Robot Pushing Dataset (action-conditioned)
BAIR Robot Pushing Dataset (action-conditioned)
Yellow frames are context frames while Green frames are predicted frames.
Samples in the paper
Samples in the paper
More samples
More samples
Human3.6M Dataset
Human3.6M Dataset
Yellow frames are context frames while Green frames are predicted frames.
Samples in the paper
Samples in the paper
More Samples
More Samples
Robot Pushing Dataset
Robot Pushing Dataset
Yellow frames are context frames while Green frames are predicted frames.
Samples in the paper
Samples in the paper
More samples
More samples