MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment

The proposed method consists of four components: feature extractor using ViT, transposed attention block, scale swin transformer block, and a dual branch structure for patch-weighted quality prediction.

Data and Resources

Cite this as

Sidi Yang, Tianhe Wu, Shuwei Shi, Shanshan Lao, Yuan Gong, Mingdeng Cao, Jiahao Wang, Yujiu Yang (2024). Dataset: MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment. https://doi.org/10.57702/nb5q5ea2

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Sidi Yang
More Authors
Tianhe Wu
Shuwei Shi
Shanshan Lao
Yuan Gong
Mingdeng Cao
Jiahao Wang
Yujiu Yang
Homepage https://github.com/IIGROUP/MANIQA