Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning
This addresses the challenge of generating high-quality translated videos for applications like video editing and synthesis, though it appears incremental as it builds on existing unsupervised translation frameworks.
The paper tackled the problem of unsupervised video-to-video translation, which often fails to produce realistic, semantic-preserving, and consistent videos, by proposing UVIT, a model that uses style-content decomposition and self-supervised learning to achieve photo-realistic and spatio-temporal consistent results, with experimental validation showing superiority over existing methods.
Existing unsupervised video-to-video translation methods fail to produce translated videos which are frame-wise realistic, semantic information preserving and video-level consistent. In this work, we propose UVIT, a novel unsupervised video-to-video translation model. Our model decomposes the style and the content, uses the specialized encoder-decoder structure and propagates the inter-frame information through bidirectional recurrent neural network (RNN) units. The style-content decomposition mechanism enables us to achieve style consistent video translation results as well as provides us with a good interface for modality flexible translation. In addition, by changing the input frames and style codes incorporated in our translation, we propose a video interpolation loss, which captures temporal information within the sequence to train our building blocks in a self-supervised manner. Our model can produce photo-realistic, spatio-temporal consistent translated videos in a multimodal way. Subjective and objective experimental results validate the superiority of our model over existing methods. More details can be found on our project website: https://uvit.netlify.com