VDFP: Video Deflickering with Flicker-banding Priors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Zhiyi, Zhu, Libo, Zhou, Zihan, Zhang, Yulun, Yang, Xiaokang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913150777950208
author Zhou, Zhiyi
Zhu, Libo
Zhou, Zihan
Zhang, Yulun
Yang, Xiaokang
author_facet Zhou, Zhiyi
Zhu, Libo
Zhou, Zihan
Zhang, Yulun
Yang, Xiaokang
contents Capturing digital screens with smartphones frequently induces severe banding due to hardware synchronization mismatches. Existing video restoration methods struggle with these structured, periodic luminance fluctuations, often resulting in residual artifacts or over-smoothed textures. We firstly construct DeViD, a real-world dataset in various scenes to deal with the lack of available datasets. Then we propose VDFP (Video Deflickering with Flicker-banding Priors), a novel perception-guided generation framework. First, we introduce a Degradation Field Modeling Based on Rolling Shutter Mechanism (DFM) capable of synthesizing complex multi-banding scenarios. Second, we present a spatial-temporal continuous prior perception (CPP). Unlike traditional binary segmentation, this module is optimized via a Flicker-Aware Mean Squared Error (FA-MSE) to capture the luminance transitions. By zero-initializing an augmented input layer, our model preserves pre-trained generative priors as well as spatial-temporal prior perception. Extensive experiments demonstrate that VDFP significantly outperforms other methods, eliminating complex banding with high-fidelity spatial details and temporal consistency. Our dataset and code will be released at https://github.com/ZhiyiZZhou/VDFP.
format Preprint
id arxiv_https___arxiv_org_abs_2605_21079
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VDFP: Video Deflickering with Flicker-banding Priors
Zhou, Zhiyi
Zhu, Libo
Zhou, Zihan
Zhang, Yulun
Yang, Xiaokang
Computer Vision and Pattern Recognition
Capturing digital screens with smartphones frequently induces severe banding due to hardware synchronization mismatches. Existing video restoration methods struggle with these structured, periodic luminance fluctuations, often resulting in residual artifacts or over-smoothed textures. We firstly construct DeViD, a real-world dataset in various scenes to deal with the lack of available datasets. Then we propose VDFP (Video Deflickering with Flicker-banding Priors), a novel perception-guided generation framework. First, we introduce a Degradation Field Modeling Based on Rolling Shutter Mechanism (DFM) capable of synthesizing complex multi-banding scenarios. Second, we present a spatial-temporal continuous prior perception (CPP). Unlike traditional binary segmentation, this module is optimized via a Flicker-Aware Mean Squared Error (FA-MSE) to capture the luminance transitions. By zero-initializing an augmented input layer, our model preserves pre-trained generative priors as well as spatial-temporal prior perception. Extensive experiments demonstrate that VDFP significantly outperforms other methods, eliminating complex banding with high-fidelity spatial details and temporal consistency. Our dataset and code will be released at https://github.com/ZhiyiZZhou/VDFP.
title VDFP: Video Deflickering with Flicker-banding Priors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.21079