Circular quasiconformal deturbulence: Geometry-based restoration from multiple turbulent frames
Neurocomputing · 2026-10 · 698 · 134277
DOI: 10.1016/j.neucom.2026.134277 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neurocomputing, 2026-10. Verfasst von Chu Chen und 2 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Gefördert von: University Grants Committee.
Abstract (Originalsprache)
Imaging through inhomogeneous media often results in severe distortions, posing significant challenges to downstream image-processing tasks. The lack of clean paired images makes supervised learning impractical, motivating unsupervised restoration approaches. In this work, we propose the Circular Quasi-Conformal Deturbulence (CQCD) framework, an unsupervised approach that reconstructs distortion-free images from multiple frames using a circular architecture. The framework minimizes reconstruction errors by jointly estimating forward and backward transformations between distorted observations and the restored image. A key advancement of CQCD is the integration of computational quasi-conformal geometry, which encourages bijective non-rigid deformations and improves the well-posedness of both forward and inverse mappings for cycle consistency. The deformation field is further regularized to preserve structural coherence and reduce non-physical artifacts such as folding or tearing. Additionally, tight-frame blocks are employed to effectively encode distortion-sensitive features, enhancing the precision of the restoration process. To assess the effectiveness of the proposed framework, extensive evaluations are conducted on synthetic and real-world image datasets. Experimental findings indicate that CQCD not only surpasses existing state-of-the-art deturbulence techniques in restoration quality but also achieves highly accurate deformation field estimation.
Förderung
- University Grants Committee
Zitieren
APA
Chen, C., Zhang, H., & Lui, L. M. (2026). Circular quasiconformal deturbulence: Geometry-based restoration from multiple turbulent frames. Neurocomputing, 698, 134277. https://doi.org/10.1016/j.neucom.2026.134277
Vancouver
Chen C, Zhang H, Lui LM. Circular quasiconformal deturbulence: Geometry-based restoration from multiple turbulent frames. Neurocomputing. 2026;698:134277. doi:10.1016/j.neucom.2026.134277
BibTeX
@article{Chen2026,
author = {Chen, Chu and Zhang, Han and Lui, Lok Ming},
title = {Circular quasiconformal deturbulence: Geometry-based restoration from multiple turbulent frames},
journal = {Neurocomputing},
year = {2026},
volume = {698},
pages = {134277},
doi = {10.1016/j.neucom.2026.134277}
}
EUVIMED