Optical Flow Estimation from a Single Motion-blurred Image

TL;DR

This paper introduces a novel end-to-end transformer-based framework for estimating optical flow from a single motion-blurred image, enabling applications like deblurring and moving object segmentation.

Contribution

It presents a new method that estimates optical flow directly from a single motion-blurred image without explicit frame supervision, using a transformer network architecture.

Findings

Effective on synthetic and real datasets

Improves performance in deblurring and segmentation tasks

Outperforms existing approaches in accuracy

Abstract

In most of computer vision applications, motion blur is regarded as an undesirable artifact. However, it has been shown that motion blur in an image may have practical interests in fundamental computer vision problems. In this work, we propose a novel framework to estimate optical flow from a single motion-blurred image in an end-to-end manner. We design our network with transformer networks to learn globally and locally varying motions from encoded features of a motion-blurred input, and decode left and right frame features without explicit frame supervision. A flow estimator network is then used to estimate optical flow from the decoded features in a coarse-to-fine manner. We qualitatively and quantitatively evaluate our model through a large set of experiments on synthetic and real motion-blur datasets. We also provide in-depth analysis of our model in connection with related approaches to highlight the effectiveness and favorability of our approach. Furthermore, we showcase the applicability of the flow estimated by our method on deblurring and moving object segmentation tasks.