State-of-the-art image restoration methods currently face challenges in terms of computational requirements and performance, making them impractical for deployment on edge devices such as phones and resource-limited devices.

The code is publicly available at https://github.com/jinnh/GSAD.

A three-Dimensional Look-up Table (3D LUT) is often used to transform one set of colors into another.

Label distribution learning is a powerful learning paradigm to deal with label polysemy and has been widely applied in many practical tasks.

Neural Information Processing Systems http://nips.cc/

Moreover, CNNs and Transformers struggle to capture global degradation due to their limited receptive fields.

BIR-D not only has t he capability t o r estore ( a) l inear inverse problems when t he degradation function i s known.