Abstract
We present simple video-specific autoencoders that enables human-controllable video exploration. This includes a wide variety of analytic tasks such as (but not limited to) spatial and temporal super-resolution, spatial and temporal editing, object removal, video textures, average video exploration, and correspondence estimation within and across videos. Prior work has independently looked at each of these problems and proposed different formulations. In this work, we observe that a simple autoencoder trained (from scratch) on multiple frames of a specific video enables one to perform a large variety of video processing and editing tasks. Our tasks are enabled by two key observations: (1) latent codes learned by the autoencoder capture spatial and temporal properties of that video and (2) autoencoders can project out-of-sample inputs onto the video-specific manifold. For e.g. (1) interpolating latent codes enables temporal super-resolution and user-controllable video textures; (2) manifold reprojection enables spatial super-resolution, object removal, and denoising without training for any of the tasks. Importantly, a two-dimensional visualization of latent codes via principal component analysis acts as a tool for users to both visualize and intuitively control video edits. Finally, we quantitatively contrast our approach with the prior art and found that without any supervision and task-specific knowledge, our approach can perform comparably to supervised approaches specifically trained for a task.
Abstract (translated)
URL
https://arxiv.org/abs/2103.17261
