Sign in

INR-V: A Continuous Representation Space for Video-based Generative Tasks

By Bipasha Sen and others
Generating videos is a complex task that is accomplished by generating a set of temporally coherent images frame-by-frame. This limits the expressivity of videos to only image-based operations on the individual video frames needing network designs to obtain temporally coherent trajectories in the underlying image space. We propose INR-V, a... Show more
April 3, 2023
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
INR-V: A Continuous Representation Space for Video-based Generative Tasks
Click on play to start listening