Preprint
Aug 2026
PixelSR: Efficient Screen Content Super-Resolution via Pixel Classification
Experiments show the PixelSR achieves state-of-the-art performance with shorter inference time in screen content super-resolution, and utilizes the properties of self-repetitiveness and redundancy in screen content to speed up inference without the loss of model performance.
Zhiheng Li, Lei Chen, Jie Zhou et al.
· 0 citations