Generalized Portrait Quality Assessment
This work addresses the need for reliable portrait quality assessment in applications like smartphone photography, representing an incremental improvement over existing methods.
The paper tackles the problem of automated portrait quality assessment by introducing FHIQA, a learning-based approach that uses semantic-aware quality score rescaling to improve fine-grained image quality metrics, achieving robust generalization across diverse scenes as validated on the PIQ23 benchmark.
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.