Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Liu, Kangliang"'
Scene text image super-resolution has significantly improved the accuracy of scene text recognition. However, many existing methods emphasize performance over efficiency and ignore the practical need for lightweight solutions in deployment scenarios.
Externí odkaz:
http://arxiv.org/abs/2403.13330
Transformer is beneficial for image denoising tasks since it can model long-range dependencies to overcome the limitations presented by inductive convolutional biases. However, directly applying the transformer structure to remove noise is challengin
Externí odkaz:
http://arxiv.org/abs/2304.06346