A vertical residual autoencoder with auxiliary input-feature injection improves synthetic license-plate image denoising and deblurring metrics over simple autoencoder, GAN, and flow baselines.
In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
VRAE: Vertical Residual Autoencoder for License Plate Denoising and Deblurring
A vertical residual autoencoder with auxiliary input-feature injection improves synthetic license-plate image denoising and deblurring metrics over simple autoencoder, GAN, and flow baselines.