About this document
SwinIR: Image Restoration with Transformers by levi vasconcelos is a document available to read on EtoBox.
This document describes a new method called SwinIR that uses Swin Transformers for image restoration tasks like super resolution, denoising, and compression artifact reduction. SwinIR achieves better performance than existing CNN-based methods using fewer parameters by leveraging the advantages of both CNNs and Transformers for modeling local dependencies and long-range interactions.
- Author
- levi vasconcelos
- Language
- EN