We present PAT, a transformer-based network that learns complex temporal...
Existing person image generative models can do either image generation o...
Generating grammatically and semantically correct captions in video
capt...
Transformers have recently been shown to generate high quality images fr...
We present SILT, a Self-supervised Implicit Lighting Transfer method. Un...
We present a new end-to-end learning framework to obtain detailed and
sp...
We present a novel method to learn temporally consistent 3D reconstructi...
We present a novel method to improve the accuracy of the 3D reconstructi...
We present a generalised self-supervised learning approach for monocular...
Existing methods for stereo work on narrow baseline image pairs giving
l...
With the increasing global popularity of self-driving cars, there is an
...
We introduce the first approach to solve the challenging problem of
unsu...
Existing techniques for dynamic scene reconstruction from multiple
wide-...
Light-field video has recently been used in virtual and augmented realit...
This paper presents an approach for reconstruction of 4D temporally cohe...