TMSR: Tiny Multi-path CNNs for Super Resolution
This is an incremental improvement for efficient image super-resolution, targeting applications with limited computational resources.
The paper tackles the problem of super-resolution with very small models by proposing TMSR, a tiny multi-path CNN under 5k parameters, which achieves competitive image quality in terms of PSNR and SSIM compared to related works.
In this paper, we proposed a tiny multi-path CNN-based Super-Resolution (SR) method, called TMSR. We mainly refer to some tiny CNN-based SR methods, under 5k parameters. The main contribution of the proposed method is the improved multi-path learning and self-defined activated function. The experimental results show that TMSR obtains competitive image quality (i.e. PSNR and SSIM) compared to the related works under 5k parameters.