DiMoSR, a lightweight super-resolution network using multi-branch dilated convolutions and feature modulation, reports state-of-the-art PSNR/SSIM on four benchmark datasets at x4 upscaling.
Fast, accurate, and lightweight super-resolution with cascading residual network
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DiMoSR: Feature Modulation via Multi-Branch Dilated Convolutions for Efficient Image Super-Resolution
DiMoSR, a lightweight super-resolution network using multi-branch dilated convolutions and feature modulation, reports state-of-the-art PSNR/SSIM on four benchmark datasets at x4 upscaling.