Restoration of Video Frames from a Single Blurred Image with Motion Understanding
This addresses the challenge of video restoration from blurred images for applications in computer vision, though it is incremental as it builds on prior single-image deblurring work.
The paper tackles the problem of generating clean video frames from a single motion-blurred image, achieving results through a novel encoder-decoder framework with spatial transformer networks, as demonstrated on datasets including camera rotation blurs and high-speed video motion blurs.
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.