ParagonSR. ParagonSR is a reparameterizable CNN-hybrid for restoration, integrating Transformer-style components. It uses an Inception-style depthwise conv for multi-scale context and a powerful Gated-FFN for feature transformation, while fusing into a simple CNN for fast inference.

github.com/Phhofm/ParagonSR

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

No recent activity.