VDFP: Video Deflickering with Flicker-banding Priors

TL;DR

This paper introduces VDFP, a novel video deflickering framework that effectively reduces flicker-banding artifacts in smartphone-captured screen videos by modeling degradation and perception priors, supported by a new dataset.

Contribution

The paper presents a new perception-guided generation framework with a degradation model and a continuous prior perception module, along with a real-world dataset for flicker-banding scenarios.

Findings

VDFP outperforms existing methods in eliminating banding artifacts.

The proposed model preserves spatial details and temporal consistency.

Extensive experiments validate the effectiveness of VDFP.

Abstract

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.