Video colorization dataset and benchmark

Simple item page
dc.contributor.authorAbeysinghe, C
dc.contributor.authorWijesinghe, T
dc.contributor.authorWijesinghe, C
dc.contributor.authorJayathilake, L
dc.contributor.authorThayasivam, U
dc.date.accessioned2019-09-05T04:45:38Z
dc.date.available2019-09-05T04:45:38Z
dc.description.abstractVideo colorization is the process of assigning realistic, plausible colors to a grayscale video. Compared to its peer, image colorization, video colorization is a relatively unexplored area in computer vision. Most of the models available for video colorization are extensions of image colorization, and hence are unable to address some unique issues in video domain. In this paper, we evaluate the applicability of image colorization techniques for video colorization, identifying problems inherent to videos and attributes affecting them. We develop a dataset and benchmark to measure the effect of such attributes to video colorization quality and demonstrate how our benchmark aligns with human evaluations.en_US
dc.identifier.conferenceMoratuwa Engineering Research Conference - MERCon 2019en_US
dc.identifier.departmentDepartment of Computer Science and Engineeringen_US
dc.identifier.facultyEngineeringen_US
dc.identifier.placeMoraruwa, Sri Lankaen_US
dc.identifier.urihttp://dl.lib.mrt.ac.lk/handle/123/14978
dc.identifier.year2019en_US
dc.language.isoenen_US
dc.subjectComputer visionen_US
dc.subjectMachine learningen_US
dc.subjectDeep learningen_US
dc.subjectVideo colorizationen_US
dc.subjectDataseten_US
dc.subjectBenchmarken_US
dc.titleVideo colorization dataset and benchmarken_US
dc.typeConference-Abstracten_US

Files

Collections

MERCon - 2019