Motion Deblurring of Faces

Please use this identifier to cite or link to this item: https://idr.l1.nitk.ac.in/jspui/handle/123456789/14951

Full metadata record

DC Field	Value	Language
dc.contributor.author	Anand P.
dc.contributor.author	Sumam David S.
dc.contributor.author	Sudeep K.S.
dc.date.accessioned	2021-05-05T10:16:03Z	-
dc.date.available	2021-05-05T10:16:03Z	-
dc.date.issued	2020
dc.identifier.citation	Proceedings - 5th IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2020 , Vol. , , p. 78 - 82	en_US
dc.identifier.uri	https://doi.org/10.1109/RTEICT49044.2020.9315623
dc.identifier.uri	http://idr.nitk.ac.in/jspui/handle/123456789/14951	-
dc.description.abstract	This paper evaluates learning-based data-driven models for deblurring of facial images. Existing algorithms for deblurring, when used for facial images, often fail to preserve the facial shape and identity information. The best available models, which are used for general-purpose image deblurring, are pre-trained using only facial images. The Peak Signal to Noise Ratio (PSNR) Structural Similarity Index Measure (SSIM) and Time to deblur single images are the key metrics used for evaluating the models and for finding the most efficient model for deblurring facial images. From the results, the observation is that even though the PSNR value for DeblurGANv2 model is the highest, the best trade off between PSNR, SSIM, Time to deblur and visual quality is seen in DeblurGAN model. © 2020 IEEE.	en_US
dc.title	Motion Deblurring of Faces	en_US
dc.type	Conference Paper	en_US
Appears in Collections:	2. Conference Papers

Files in This Item:

There are no files associated with this item.