Generating video stories from text prompts is a complex task. In additio...
Masked Autoencoders (MAEs) learn self-supervised representations by rand...
We present Phenaki, a model capable of realistic video synthesis, given ...
There have been remarkable successes in computer vision with deep learni...
This paper introduces a motion retargeting method that preserves
self-co...
A long-standing goal in computer vision is to capture, model, and
realis...
We present a single-image data-driven method to automatically relight im...
A deep generative model that describes human motions can benefit a wide ...
Existing deep models predict 2D and 3D kinematic poses from video that a...
Predicting future video frames is extremely challenging, as there are ma...
Extracting and predicting object structure and dynamics from videos with...
Planning has been very successful for control tasks with known environme...
Long-term human motion can be represented as a series of motion
modes---...
Much of recent research has been devoted to video prediction and generat...
We propose a recurrent neural network architecture with a Forward Kinema...
We propose a deep neural network for the prediction of future frames in
...
Object detection systems based on the deep convolutional neural network ...