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

Zhengqi Li

Abstract

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. To achieve this, we propose a novel self-supervised view generation training paradigm, where we sample and rendering virtual camera trajectories, including cyclic ones, allowing our model to learn stable view generation from a collection of single views. At test time, despite never seeing a video during training, our approach can take a single image and generate long camera trajectories comprised of hundreds of new views with realistic and diverse content. We compare our approach with recent state-of-the-art supervised view generation methods that require posed multi-view videos and demonstrate superior performance and synthesis quality.
BibTeX
@inproceedings{li2022infinitenature,
  author = {Zhengqi Li},
  title = {{InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images}},
  booktitle = {European Conference on Computer Vision},
  year = {2022},
  doi = {10.1007/978-3-031-19769-7\_30},
}
Figure