We introduce DiscoBox, a novel framework that jointly learns instance
se...
Conventional CNNs for texture synthesis consist of a sequence of
(de)-co...
Video-to-video synthesis (vid2vid) aims at converting an input semantic
...
Learning to synthesize high frame rate videos via interpolation requires...
Inverse rendering aims to estimate physical scene attributes (e.g.,
refl...
In this paper, we present a simple yet effective padding scheme that can...
We present an approach for high-resolution video frame prediction by
con...
We study the problem of video-to-video synthesis, whose goal is to learn...
Existing deep learning based image inpainting methods use a standard
con...
The ability to edit materials of objects in images is desirable by many
...
Due to the abundance of 2D product images from the Internet, developing
...