Nature

Many people have no mental imagery. What’s going on in their brains?

Think about your breakfast this morning. Can you imagine the pattern on your coffee mug? The sheen of the jam on your half-eaten toast? Most of us can call up such pictures in our minds. We can ...
GitHub

Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption

(2025-09-15) The inference code of A-FINE is intergrated into the excellent PyIQA codeframe. Please find the detailed usage here. (2025-04-14) We release the DiffIQA dataset. (2025-04-14) We release ...
IEEE

Visual State Space Model With Graph-Based Feature Aggregation for No-Reference Image Quality Assessment

Abstract: Inspired by the human visual system (HVS), no-reference image quality assessment (NR-IQA) has made significant progress without relying on perfect reference images. The HVS is primarily ...
IEEE

Denoised Semantic Features for Local Consistent No-reference Image Quality Assessment

Abstract: Multi-dataset no-reference image quality assessment (NR-IQA) aims to deliver consistent image quality evaluation across a variety of contexts, empowering platform developers to optimize ...
GitHub

MR-FIQA: Face Image Quality Assessment with Multi-Reference Representations from Synthetic Data Generation

Stage-1 Generation: The code in this stage is mainly built on the PyTorch framework. Specifically, it requires PyTorch version 1.10.0 or later, along with the ...