An authentic face restoration system is becoming increasingly demanding ...
The one-shot talking-head synthesis task aims to animate a source image ...
Many applications can benefit from personalized image generation models,...
This paper proposes a method for generating images of customized objects...
Image composition plays an important role in the quality of a photo. How...
Ideally, 360 imagery could inherit the deep convolutional neural
network...
Standard video encoders developed for conventional narrow field-of-view ...
While 360 cameras offer tremendous new possibilities in vision,
graphics...
360^∘ video requires human viewers to actively control "where" to
look w...
We introduce the novel task of Pano2Vid - automatic cinematography in
pa...
In a wearable camera video, we see what the camera wearer sees. While th...
Current approaches for activity recognition often ignore constraints on
...
Unconstrained video recognition and Deep Convolution Network (DCN) are t...