Can I read LDMVFI: Video Frame Interpolation with Latent Diffusion Models on EtoBox?

LDMVFI: Video Frame Interpolation with Latent Diffusion Models by Danier, Duolikun; Zhang, Fan; Bull, David is a scholarly article available to read on EtoBox.

What is LDMVFI: Video Frame Interpolation with Latent Diffusion Models about?

Existing works on video frame interpolation (VFI) mostly employ deep neural networks that are trained by minimizing the L1, L2, or deep feature space distance (e.g. VGG loss) between their outputs and ground-truth frames. However, recent works have shown that these metrics are poor indicators of perceptual VFI quality. Towards developing perceptually-oriented VFI methods, in this work we propose latent diffusion model-based VFI, LDMVFI. This approaches the VFI problem from a generative perspective by formulating it as a conditional generation problem. As the first effort to address VFI using latent diffusion models, we rigorously benchmark our method on common test sets used in the existing VFI literature. Our quantitative experiments and user study indicate that LDMVFI is able to interpolate video content with favorable perceptual quality compared to the state of the art, even in the high-resolution regime. Our code is available at https://github.com/danier97/LDMVFI.

Author

Danier, Duolikun; Zhang, Fan; Bull, David

Published

2023

Language

EN