The paper builds a synthetic motion-blur tracking benchmark, finds light blur helps and heavy blur hurts most trackers, and proposes fine-tuning a DeblurGAN discriminator to selectively deblur frames, improving six of seven tested trackers.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Effects of Blur and Deblurring to Visual Object Tracking
The paper builds a synthetic motion-blur tracking benchmark, finds light blur helps and heavy blur hurts most trackers, and proposes fine-tuning a DeblurGAN discriminator to selectively deblur frames, improving six of seven tested trackers.