MAXIM: Multi-Axis MLP for Image Processing

MAXIM: Multi-Axis MLP for Image Processing

GitHub – google-research/maxim: [CVPR 2022 Oral] Official repository for “MAXIM: Multi-Axis MLP for Image Processing”. SOTA for denoising, deblurring, deraining, dehazing, and enhancement.

Multi-Axis MLP for Image Processing (MAXIM) is a state-of-the-art deep learning framework developed by Google Research for low-level vision tasks such as image denoising, deblurring, deraining, dehazing, and enhancement. Presented at CVPR 2022 (Oral, Best Paper Nomination), MAXIM leverages multi-axis MLPs to outperform traditional convolutional approaches. The repository includes pre-trained models, demos, and implementation in both TensorFlow and PyTorch

Source: github.com/google-research/maxim?tab=readme-ov-file