Salvato in:
Dettagli Bibliografici
Autori principali: Lai, Ka Chung, Cetinkaya, Ahmet
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2512.00700
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912738305900544
author Lai, Ka Chung
Cetinkaya, Ahmet
author_facet Lai, Ka Chung
Cetinkaya, Ahmet
contents We propose a new neural network architecture called CAR-net (CAscade Refinement Network) to deblur images that are subject to rotational motion blur. Our architecture is specifically designed for the semi-blind scenarios where only noisy information of the rotational motion blur angle is available. The core of our approach is progressive refinement process that starts with an initial deblurred estimate obtained from frequency-domain inversion; A series of refinement stages take the current deblurred image to predict and apply residual correction to the current estimate, progressively suppressing artifacts and restoring fine details. To handle parameter uncertainty, our architecture accommodates an optional angle detection module which can be trained end-to-end with refinement modules. We provide a detailed description of our architecture and illustrate its efficiency through experiments using both synthetic and real-life images. Our code and model as well as the links to the datasets are available at https://github.com/tony123105/CAR-Net
format Preprint
id arxiv_https___arxiv_org_abs_2512_00700
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CAR-Net: A Cascade Refinement Network for Rotational Motion Deblurring under Angle Information Uncertainty
Lai, Ka Chung
Cetinkaya, Ahmet
Computer Vision and Pattern Recognition
We propose a new neural network architecture called CAR-net (CAscade Refinement Network) to deblur images that are subject to rotational motion blur. Our architecture is specifically designed for the semi-blind scenarios where only noisy information of the rotational motion blur angle is available. The core of our approach is progressive refinement process that starts with an initial deblurred estimate obtained from frequency-domain inversion; A series of refinement stages take the current deblurred image to predict and apply residual correction to the current estimate, progressively suppressing artifacts and restoring fine details. To handle parameter uncertainty, our architecture accommodates an optional angle detection module which can be trained end-to-end with refinement modules. We provide a detailed description of our architecture and illustrate its efficiency through experiments using both synthetic and real-life images. Our code and model as well as the links to the datasets are available at https://github.com/tony123105/CAR-Net
title CAR-Net: A Cascade Refinement Network for Rotational Motion Deblurring under Angle Information Uncertainty
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.00700