The U-Net based GLOW for Optical-Flow-free Video Interframe Generation

TL;DR

This paper introduces a novel optical-flow-free video frame interpolation method using a U-Net based invertible generative flow network with a new latent space consistency loss, ensuring stable and semantically consistent intermediate frames.

Contribution

It presents the first use of invertible networks for video interpolation, eliminating the need for optical flow and complex occlusion handling.

Findings

Feasibility demonstrated through experiments

Stable, flicker-free intermediate frames achieved

Proposed method outperforms traditional optical flow-based approaches

Abstract

Video frame interpolation is the task of creating an interframe between two adjacent frames along the time axis. So, instead of simply averaging two adjacent frames to create an intermediate image, this operation should maintain semantic continuity with the adjacent frames. Most conventional methods use optical flow, and various tools such as occlusion handling and object smoothing are indispensable. Since the use of these various tools leads to complex problems, we tried to tackle the video interframe generation problem without using problematic optical flow . To enable this , we have tried to use a deep neural network with an invertible structure, and developed an U-Net based Generative Flow which is a modified normalizing flow. In addition, we propose a learning method with a new consistency loss in the latent space to maintain semantic temporal consistency between frames. The resolution of the generated image is guaranteed to be identical to that of the original images by using an invertible network. Furthermore, as it is not a random image like the ones by generative models, our network guarantees stable outputs without flicker. Through experiments, we \sam {confirmed the feasibility of the proposed algorithm and would like to suggest the U-Net based Generative Flow as a new possibility for baseline in video frame interpolation. This paper is meaningful in that it is the world's first attempt to use invertible networks instead of optical flows for video interpolation.