Single Image Rolling Shutter Removal with Diffusion Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yang, Zhanglei, Li, Haipeng, Hong, Mingbo, Zhang, Chen-Lin, Li, Jiajun, Liu, Shuaicheng
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909533170827264
author Yang, Zhanglei
Li, Haipeng
Hong, Mingbo
Zhang, Chen-Lin
Li, Jiajun
Liu, Shuaicheng
author_facet Yang, Zhanglei
Li, Haipeng
Hong, Mingbo
Zhang, Chen-Lin
Li, Jiajun
Liu, Shuaicheng
contents We present RS-Diffusion, the first Diffusion Models-based method for single-frame Rolling Shutter (RS) correction. RS artifacts compromise visual quality of frames due to the row-wise exposure of CMOS sensors. Most previous methods have focused on multi-frame approaches, using temporal information from consecutive frames for the motion rectification. However, few approaches address the more challenging but important single frame RS correction. In this work, we present an ``image-to-motion" framework via diffusion techniques, with a designed patch-attention module. In addition, we present the RS-Real dataset, comprised of captured RS frames alongside their corresponding Global Shutter (GS) ground-truth pairs. The GS frames are corrected from the RS ones, guided by the corresponding Inertial Measurement Unit (IMU) gyroscope data acquired during capture. Experiments show that RS-Diffusion surpasses previous single-frame RS methods, demonstrates the potential of diffusion-based approaches, and provides a valuable dataset for further research.
format Preprint
id arxiv_https___arxiv_org_abs_2407_02906
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Single Image Rolling Shutter Removal with Diffusion Models
Yang, Zhanglei
Li, Haipeng
Hong, Mingbo
Zhang, Chen-Lin
Li, Jiajun
Liu, Shuaicheng
Computer Vision and Pattern Recognition
We present RS-Diffusion, the first Diffusion Models-based method for single-frame Rolling Shutter (RS) correction. RS artifacts compromise visual quality of frames due to the row-wise exposure of CMOS sensors. Most previous methods have focused on multi-frame approaches, using temporal information from consecutive frames for the motion rectification. However, few approaches address the more challenging but important single frame RS correction. In this work, we present an ``image-to-motion" framework via diffusion techniques, with a designed patch-attention module. In addition, we present the RS-Real dataset, comprised of captured RS frames alongside their corresponding Global Shutter (GS) ground-truth pairs. The GS frames are corrected from the RS ones, guided by the corresponding Inertial Measurement Unit (IMU) gyroscope data acquired during capture. Experiments show that RS-Diffusion surpasses previous single-frame RS methods, demonstrates the potential of diffusion-based approaches, and provides a valuable dataset for further research.
title Single Image Rolling Shutter Removal with Diffusion Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.02906