swz30/Restormer
A Transformer-based model achieving state-of-the-art results on image restoration tasks including motion deblurring, image deraining, denoising, and defocus deblurring.
Not currently ranked — collecting fresh signals.
star history
Restormer is an efficient Transformer architecture designed for high-resolution image restoration. It leverages channel and spatial attention mechanisms to process features at different scales. The model achieves state-of-the-art performance on multiple low-level vision tasks including motion deblurring, image deraining, Gaussian and real-world denoising, and defocus deblurring. It is implemented in PyTorch and released with training codes and pre-trained weights.
Frequently asked
- What is swz30/Restormer?
- A Transformer-based model achieving state-of-the-art results on image restoration tasks including motion deblurring, image deraining, denoising, and defocus deblurring.
- Is Restormer open source?
- Yes — swz30/Restormer is open source, released under the MIT license.
- What language is Restormer written in?
- swz30/Restormer is primarily written in Python.
- How popular is Restormer?
- swz30/Restormer has 2.6k stars on GitHub.
- Where can I find Restormer?
- swz30/Restormer is on GitHub at https://github.com/swz30/Restormer.