MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment
What it is
MANIQA is a PyTorch implementation of a deep learning model for no-reference image quality assessment (NR-IQA). It uses a Vision Transformer (ViT) backbone combined with Transposed Attention Blocks and Scale Swin Transformer Blocks to capture global and local interactions, enabling it to predict perceptual quality scores for images, particularly those with GAN-based distortions.
The problem it solves
Existing no-reference image quality assessment methods often fail to accurately predict quality scores for images with GAN-based distortions, which are common in modern generative AI workflows.
What you could use it for
- Automated quality scoring of generated images in GAN pipelines
- Benchmarking perceptual quality of image restoration models
- Filtering low-quality images from datasets
- Evaluating performance in NTIRE-style image quality challenges
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.