Deep Portrait Quality Assessment. A NTIRE 2024 Challenge Survey

This paper reviews the NTIRE 2024 Portrait Quality Assessment Challenge, highlighting the proposed solutions and results. This challenge aims to obtain an efficient deep neural network capable of estimating the perceptual quality of real portrait photos. The methods must generalize to diverse scenes and diverse lighting conditions (indoor, outdoor, low-light), movement, blur, and other challenging conditions. In the challenge, 140 participants registered, and 35 submitted results during the challenge period. The performance of the top 5 submissions is reviewed and provided here as a gauge for the current state-of-the-art in Portrait Quality Assessment.

1. Introduction

Portrait Quality Assessment (PQA) is becoming increasingly important in a variety of fields, from social media engagement to professional photography. The subjective nature of aesthetic appreciation, combined with the technical complexities of image capture and processing, makes PQA a challenging task. While Redi et al. [25] have explored the attributes that contribute to the perceived beauty of portraits, the utility-focused approach of Face Image Quality Assessment (FIQA) [27] underscores the diversity of criteria required for different quality assessment contexts.