Self-supervised Blur Detection from Synthetically Blurred Scenes
Loading...
Files
Identifiers
Publication date
2019-12
Advisors
Journal Title
Journal ISSN
Volume Title
Publisher
Citations
Export
Abstract
Blur detection aims at segmenting the blurred areas of a given image. Recent deep learning-based methods approach this problem by learning an end-to-end mapping between the blurred input and a binary mask representing the localization of its blurred areas. Nevertheless, the effectiveness of such deep models is limited due to the scarcity of datasets annotated in terms of blur segmentation, as blur annotation is labour intensive. In this work, we bypass the need for such annotated datasets for end-to-end learning, and instead rely on object proposals and a model for blur generation in order to produce a dataset of synthetically blurred images. This allows us to perform self-supervised learning over the generated image and ground truth blur mask pairs using CNNs, defining a framework that can be employed in purely self-supervised, weakly supervised or semi-supervised configurations. Interestingly, experimental results of such setups over the largest blur segmentation datasets available show that this approach achieves state of the art results in blur segmentation, even without ever observing any real blurred image.
Description
Publisher Copyright: © 2019 Elsevier B.V.
Keywords
Blur , Defocus , Motion , Deep learning , Self-supervised learning , Synthetic , Blur , Defocus , Motion , Deep learning , Self-supervised learning , Synthetic , Blur detection , Defocus blur , Motion blur , Signal Processing , Computer Vision and Pattern Recognition , Funding Info , This research was partially funded by the Basque Government’s Industry Department under the ELKARTEK program’s project ONKOIKER under agreement KK2018/00090. We thank the Spanish project TIN2016- 79717-R and mention Generalitat de Catalunya CERCA Program. , This research was partially funded by the Basque Government’s Industry Department under the ELKARTEK program’s project ONKOIKER under agreement KK2018/00090. We thank the Spanish project TIN2016- 79717-R and mention Generalitat de Catalunya CERCA Program.
Type
Citation
Alvarez-Gila , A , Galdran , A , Garrote , E & Van de Weijer , J 2019 , ' Self-supervised Blur Detection from Synthetically Blurred Scenes ' , Image and Vision Computing , vol. unknown , 103804 . https://doi.org/10.1016/j.imavis.2019.08.008