Generalized Portrait Quality Assessment

Nicolas Chahine, Sira Ferradans, Javier Vazquez-Corral, Jean Ponce
2/14/2024
cs.CV

Official code: DXOMARK-Research/PIQ2023 (108 stars, last commit 2024-03-14).

Abstract

Automated and robust portrait quality assessment (PQA) is of paramount importance in high-impact applications such as smartphone photography. This paper presents FHIQA, a learning-based approach to PQA that introduces a simple but effective quality score rescaling method based on image semantics, to enhance the precision of fine-grained image quality metrics while ensuring robust generalization to various scene settings beyond the training dataset. The proposed approach is validated by extensive experiments on the PIQ23 benchmark and comparisons with the current state of the art. The source code of FHIQA will be made publicly available on the PIQ23 GitHub repository at https://github.com/DXOMARK-Research/PIQ2023.

View on arXivView PDF

Code Implementations(1)

DXOMARK-Research/PIQ2023Official100%
1082Python, Jupyter NotebookMar 16, 20232 years ago

Similar Papers

Dual-Branch Network for Portrait Image Quality Assessment

86% match1 repo192024

An Image Quality Assessment Dataset for Portraits

86% match1 repo1082026

Global-Local Image Perceptual Score (GLIPS): Evaluating Photorealistic Quality of AI-Generated Images

83% match2024

SQAD: Automatic Smartphone Camera Quality Assessment and Benchmarking

82% match1 repo282026

HiRQA: Hierarchical Ranking and Quality Alignment for Opinion-Unaware Image Quality Assessment

82% match2025

Adaptive Mixed-Scale Feature Fusion Network for Blind AI-Generated Image Quality Assessment

82% match1 repo102024

Cite this paper

@article{chahine2024generalized,
  title  = {Generalized Portrait Quality Assessment},
  author = {Nicolas Chahine and Sira Ferradans and Javier Vazquez-Corral and Jean Ponce},
  year   = {2024},
  eprint = {2402.09178},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.09178v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.09178.svg)](https://codeofpaper.com/paper/2402.09178)

Discussion