A FRACTAL DEEP IMAGE PRIOR WITH RELIABILITY-WEIGHTED CHARBONNIER FIDELITY FOR SALT-AND-PEPPER IMAGE DENOISING
Fractals · 30.10.2026
DOI: 10.1142/s0218348x26501707 ↗Kurz gefasst
Fachartikel in der Zeitschrift Fractals, online erschienen am 30.10.2026. Verfasst von ZHIHUI TU und 2 weiteren Autor:innen. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Salt-and-pepper Noise (SPN) is a challenging impulsive degradation because a small fraction of severely corrupted pixels can dominate quadratic observation models. However, quadratic data-fidelity terms remain common in unsupervised and hybrid approaches used for SPN removal, despite their sensitivity to sparse extreme residuals. In this paper, we propose RW-FracDIP, an unsupervised Fractal Deep Image Prior with Reliability-weighted Charbonnier Fidelity for SPN removal. RW-FracDIP combines Fractal Image Coding (FIC), Total Variation (TV) regularization, and DIP within a unified formulation, in which the quadratic observation term is replaced by a reliability-weighted Charbonnier fidelity and the reliability map is estimated directly from the noisy image to downweight suspected impulse pixels. The resulting formulation is optimized by an ADMM-style alternating scheme that preserves the complementary roles of fractal self-similarity, TV regularization, and the deep prior. Across five standard grayscale images and four SPN levels, RW-FracDIP achieves the best PSNR in all tested settings and the best SSIM in most of them against DnCNN, DIP, L1/TV, and a FIC+DIP+TV baseline, indicating robustness under impulsive corruption.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
TU, Z., NIU, W., & LU, J. (2026). A FRACTAL DEEP IMAGE PRIOR WITH RELIABILITY-WEIGHTED CHARBONNIER FIDELITY FOR SALT-AND-PEPPER IMAGE DENOISING. Fractals. https://doi.org/10.1142/s0218348x26501707
Vancouver
TU Z, NIU W, LU J. A FRACTAL DEEP IMAGE PRIOR WITH RELIABILITY-WEIGHTED CHARBONNIER FIDELITY FOR SALT-AND-PEPPER IMAGE DENOISING. Fractals. 2026. doi:10.1142/s0218348x26501707
BibTeX
@article{TU2026,
author = {TU, ZHIHUI and NIU, WEIHANG and LU, JIAN},
title = {A FRACTAL DEEP IMAGE PRIOR WITH RELIABILITY-WEIGHTED CHARBONNIER FIDELITY FOR SALT-AND-PEPPER IMAGE DENOISING},
journal = {Fractals},
year = {2026},
doi = {10.1142/s0218348x26501707}
}
EUVIMED