Perpetual View Generation

2 papers with code • 1 benchmarks • 1 datasets

Perpetual View Generation is the task of generating long-range novel views by flying into a given image.

Datasets


Most implemented papers

Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image

google-research/google-research ICCV 2021

We introduce the problem of perpetual view generation - long-range generation of novel views corresponding to an arbitrarily long camera trajectory given a single image.

InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images

google-research/google-research 22 Jul 2022

We present a method for learning to generate unbounded flythrough videos of natural scenes starting from a single view, where this capability is learned from a collection of single photographs, without requiring camera poses or even multiple views of each scene.