解决手机拍屏幕时的条纹闪烁问题，保留细节和时间一致性。
VDFP: Video Deflickering with Flicker-banding Priors
- 基于滚动快门机制建模退化场，合成复杂多条纹场景。
- 提出感知引导的时空连续先验模块，有效捕捉亮度变化过渡。
- 适用于真实场景视频修复，适合做屏幕拍摄增强的研究者。
用智能手机拍摄数字屏幕时常因硬件同步差异导致严重条纹现象。现有视频修复方法难以处理这种有结构、周期性的亮度波动，常产生残留伪影或过度平滑纹理。本文首次构建了涵盖多种场景的实拍数据集DeViD，以弥补数据缺失问题。提出VDFP（基于闪烁条纹先验的视频去闪烁）框架，采用基于滚动快门机制的退化场建模（DFM）方法，可合成复杂的多条纹场景；设计空间-时间连续先验感知（CPP）模块，通过闪烁感知均方误差（FA-MSE）优化，精准捕捉亮度过渡。通过零初始化增强输入层，模型保留预训练生成先验及时空感知能力。大量实验表明，VDFP显著优于现有方法，在消除复杂条纹的同时保持高保真空间细节与时间一致性。代码与数据集将开源于https://github.com/ZhiyiZZhou/VDFP。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。