Restoration of Video Frames from a Single Blurred Image with Motion Understanding

TL;DR

This paper introduces a new deep learning framework that reconstructs a sequence of sharp video frames and underlying motion from a single blurred image, addressing a more complex inverse problem in video restoration.

Contribution

It presents an encoder-decoder model with spatial transformer modules for end-to-end video and motion recovery from a single blurred image, a novel approach in this domain.

Findings

Effective in restoring videos from blurred images across different datasets

Demonstrates robustness to various types of motion blur

Outperforms existing methods in quality and stability

Abstract

We propose a novel framework to generate clean video frames from a single motion-blurred image. While a broad range of literature focuses on recovering a single image from a blurred image, in this work, we tackle a more challenging task i.e. video restoration from a blurred image. We formulate video restoration from a single blurred image as an inverse problem by setting clean image sequence and their respective motion as latent factors, and the blurred image as an observation. Our framework is based on an encoder-decoder structure with spatial transformer network modules to restore a video sequence and its underlying motion in an end-to-end manner. We design a loss function and regularizers with complementary properties to stabilize the training and analyze variant models of the proposed network. The effectiveness and transferability of our network are highlighted through a large set of experiments on two different types of datasets: camera rotation blurs generated from panorama scenes and dynamic motion blurs in high speed videos.