Guardado en:
Detalles Bibliográficos
Autores principales: You, Jinkun, Li, Jiaxue, Zhang, Jie, Zhou, Yicong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2511.09028
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918198456090624
author You, Jinkun
Li, Jiaxue
Zhang, Jie
Zhou, Yicong
author_facet You, Jinkun
Li, Jiaxue
Zhang, Jie
Zhou, Yicong
contents Existing unsupervised image alignment methods exhibit limited accuracy and high computational complexity. To address these challenges, we propose a dense cross-scale image alignment model. It takes into account the correlations between cross-scale features to decrease the alignment difficulty. Our model supports flexible trade-offs between accuracy and efficiency by adjusting the number of scales utilized. Additionally, we introduce a fully spatial correlation module to further improve accuracy while maintaining low computational costs. We incorporate the just noticeable difference to encourage our model to focus on image regions more sensitive to distortions, eliminating noticeable alignment errors. Extensive quantitative and qualitative experiments demonstrate that our method surpasses state-of-the-art approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2511_09028
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dense Cross-Scale Image Alignment With Fully Spatial Correlation and Just Noticeable Difference Guidance
You, Jinkun
Li, Jiaxue
Zhang, Jie
Zhou, Yicong
Computer Vision and Pattern Recognition
Existing unsupervised image alignment methods exhibit limited accuracy and high computational complexity. To address these challenges, we propose a dense cross-scale image alignment model. It takes into account the correlations between cross-scale features to decrease the alignment difficulty. Our model supports flexible trade-offs between accuracy and efficiency by adjusting the number of scales utilized. Additionally, we introduce a fully spatial correlation module to further improve accuracy while maintaining low computational costs. We incorporate the just noticeable difference to encourage our model to focus on image regions more sensitive to distortions, eliminating noticeable alignment errors. Extensive quantitative and qualitative experiments demonstrate that our method surpasses state-of-the-art approaches.
title Dense Cross-Scale Image Alignment With Fully Spatial Correlation and Just Noticeable Difference Guidance
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.09028