“InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images”, Zhengqi Li, Qianqian Wang, Noah Snavely, Angjoo Kanazawa2022-07-22 (StyleGAN, video generation)⁠:

We present a method for learning to generate unbounded fly-through 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.