VDFP: Video Deflickering with Flicker-banding Priors

2026-05-20

AI Summary

This work addresses the periodic banding artifacts that arise when smartphone cameras capture digital screens due to temporal misalignment between the rolling shutter mechanism and screen refresh cycles. To tackle this challenge, the authors propose VDFP, a perception-guided generative deflickering framework. The key innovations include the first use of a rolling-shutter-aware degradation field model to synthesize realistic multi-band flicker scenarios, a spatiotemporal continuity-aware prior module, and a Flicker-Aware MSE loss combined with a zero-initialized input layer to preserve generative priors. Evaluated on the newly introduced real-world dataset DeViD, the proposed method significantly outperforms existing approaches in complex deflickering tasks, effectively removing banding artifacts while maintaining high-fidelity spatial details and temporal consistency.

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.

Problem

• video deflickering
• flicker banding
• rolling shutter
• luminance fluctuation
• video restoration

Innovation

• flicker-banding priors
• degradation field modeling
• spatial-temporal prior perception
• rolling shutter mechanism
• FA-MSE