City Scene Super-Resolution via Geometric Error Minimization

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lu, Zhengyang, Wang, Feng
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913196392054784
author Lu, Zhengyang
Wang, Feng
author_facet Lu, Zhengyang
Wang, Feng
contents Super-resolution techniques are crucial in improving image granularity, particularly in complex urban scenes, where preserving geometric structures is vital for data-informed cultural heritage applications. In this paper, we propose a city scene super-resolution method via geometric error minimization. The geometric-consistent mechanism leverages the Hough Transform to extract regular geometric features in city scenes, enabling the computation of geometric errors between low-resolution and high-resolution images. By minimizing mixed mean square error and geometric align error during the super-resolution process, the proposed method efficiently restores details and geometric regularities. Extensive validations on the SET14, BSD300, Cityscapes and GSV-Cities datasets demonstrate that the proposed method outperforms existing state-of-the-art methods, especially in urban scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2401_07272
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle City Scene Super-Resolution via Geometric Error Minimization
Lu, Zhengyang
Wang, Feng
Computer Vision and Pattern Recognition
Super-resolution techniques are crucial in improving image granularity, particularly in complex urban scenes, where preserving geometric structures is vital for data-informed cultural heritage applications. In this paper, we propose a city scene super-resolution method via geometric error minimization. The geometric-consistent mechanism leverages the Hough Transform to extract regular geometric features in city scenes, enabling the computation of geometric errors between low-resolution and high-resolution images. By minimizing mixed mean square error and geometric align error during the super-resolution process, the proposed method efficiently restores details and geometric regularities. Extensive validations on the SET14, BSD300, Cityscapes and GSV-Cities datasets demonstrate that the proposed method outperforms existing state-of-the-art methods, especially in urban scenes.
title City Scene Super-Resolution via Geometric Error Minimization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.07272