Deep Video Deblurring for Hand-held Cameras

S. Su, M. Delbracio, J. Wang, G. Sapiro, W. Heidrich, O. Wang
Spotlight presentation, (2017)

Deep Video Deblurring for Hand-held Cameras

Keywords

Motion blur from camera shake is a major problem in videos captured by hand-held devices

Abstract

Motion blur from camera shake is a major problem in videos captured by hand-held devices. Unlike single-imagedeblurring, Video-based approaches can take advantage of the abundant information that exists across neighboring frames. As a result the best performing methods rely on the alignment of nearby frames. However, aligning images is a computationally expensive and fragile procedure, and methods that aggregate information must therefore be able to identify which regions have been accurately aligned and which have not, a task that requires high level scene under-standing. In this work, we introduce a deep learning solution to video deblurring, where a CNN is trained end-to-end to learn how to accumulate information across frames.To train this network, we collected a dataset of real videos recorded with a high frame rate camera, which we use to generate synthetic motion blur for supervision. We show that the features learned from this dataset extend to deblur-ring motion blur that arises due to camera shake in a wide range of videos, and compare the quality of results to a num-ber of other baselines.

Code

DOI:

Sources

Website PDF

See all publications 2017