Perceptual and Structural Evaluation of Super-Resolution Methods
Küçük Resim Yok
Tarih
2025
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Institute of Electrical and Electronics Engineers Inc.
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
This paper examines the underlying reasons for metric performance differences among resolution enhancement methods, analyzing why deep learning-based models, while optimizing perceptual realism, often yield lower scores in traditional structural metrics. The study explores the balance between structural fidelity and perceptual quality, detailing the factors that influence this trade-off and discussing the contextual appropriateness of various metrics. While LPIPS emerges as an effective tool for evaluating perceptual realism, SSIM and FSIM remain important in tasks where structural integrity is critical. These findings highlight the importance of carefully selecting evaluation metrics in accordance with the objectives and constraints of the target application. © 2025 IEEE.
Açıklama
2025 Innovations in Intelligent Systems and Applications Conference, ASYU 2025 -- 2025-09-10 through 2025-09-12 -- Bursa -- 214381
Anahtar Kelimeler
ESRGAN, FSIM, interpolation, LPIPS, PSNR, SSIM, super-resolution
Kaynak
WoS Q Değeri
Scopus Q Değeri
N/A
