EvoIQA - Explaining Image Distortions with Evolved White-Box Logic
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918391871176704 |
|---|---|
| author | Gupta, Ruchika Bakurov, Illya Haut, Nathan Banzhaf, Wolfgang |
| author_facet | Gupta, Ruchika Bakurov, Illya Haut, Nathan Banzhaf, Wolfgang |
| contents | Traditional Image Quality Assessment (IQA) metrics typically fall into one of two extremes: rigid, hand-crafted mathematical models or "black-box" deep learning architectures that completely lack interpretability. To bridge this gap, we propose EvoIQA, a fully explainable symbolic regression framework based on Genetic Programming that Evolves explicit, human-readable mathematical formulas for image quality assessment (IQA). Utilizing a rich terminal set from the VSI, VIF, FSIM, and HaarPSI metrics, our framework inherently maps structural, chromatic, and information-theoretic degradations into observable mathematical equations. Our results demonstrate that the evolved GP models consistently achieve strong alignment between the predictions and human visual preferences. Furthermore, they not only outperform traditional hand-crafted metrics but also achieve performance parity with complex, state-of-the-art deep learning models like DB-CNN, proving that we no longer have to sacrifice interpretability for state-of-the-art performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15887 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EvoIQA - Explaining Image Distortions with Evolved White-Box Logic Gupta, Ruchika Bakurov, Illya Haut, Nathan Banzhaf, Wolfgang Computer Vision and Pattern Recognition Neural and Evolutionary Computing I.4.9; I.2.2; I.2.10; I.1.1 Traditional Image Quality Assessment (IQA) metrics typically fall into one of two extremes: rigid, hand-crafted mathematical models or "black-box" deep learning architectures that completely lack interpretability. To bridge this gap, we propose EvoIQA, a fully explainable symbolic regression framework based on Genetic Programming that Evolves explicit, human-readable mathematical formulas for image quality assessment (IQA). Utilizing a rich terminal set from the VSI, VIF, FSIM, and HaarPSI metrics, our framework inherently maps structural, chromatic, and information-theoretic degradations into observable mathematical equations. Our results demonstrate that the evolved GP models consistently achieve strong alignment between the predictions and human visual preferences. Furthermore, they not only outperform traditional hand-crafted metrics but also achieve performance parity with complex, state-of-the-art deep learning models like DB-CNN, proving that we no longer have to sacrifice interpretability for state-of-the-art performance. |
| title | EvoIQA - Explaining Image Distortions with Evolved White-Box Logic |
| topic | Computer Vision and Pattern Recognition Neural and Evolutionary Computing I.4.9; I.2.2; I.2.10; I.1.1 |
| url | https://arxiv.org/abs/2603.15887 |