RIFLE: Removal of Image Flicker-Banding via Latent Diffusion Enhancement

2025-09-29

AI Summary

Screen-capture flicker banding (FB), caused by aliasing between display luminance modulation and camera rolling-shutter timing, severely degrades image readability and perceptual quality—yet remains systematically understudied. This work pioneers FB removal as a dedicated image restoration task and proposes an end-to-end latent diffusion model (LDM)-based framework. We introduce a Flicker Prior Estimator (FPE) to explicitly model stripe structure, incorporate a Masked Loss (ML) to concentrate optimization on flicker-affected regions, and construct the first real-world paired FB dataset. Our luminance-domain stripe synthesis pipeline integrates feathered boundaries and sensor noise to enhance realism. Experiments demonstrate consistent superiority over existing reconstruction methods across mild to severe FB scenarios, achieving state-of-the-art performance in both quantitative metrics and visual quality. This work establishes a foundational benchmark—including model architecture, curated dataset, and methodology—for future FB research.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Capturing screens is now routine in our everyday lives. But the photographs of emissive displays are often influenced by the flicker-banding (FB), which is alternating bright%u2013dark stripes that arise from temporal aliasing between a camera's rolling-shutter readout and the display's brightness modulation. Unlike moire degradation, which has been extensively studied, the FB remains underexplored despite its frequent and severe impact on readability and perceived quality. We formulate FB removal as a dedicated restoration task and introduce Removal of Image Flicker-Banding via Latent Diffusion Enhancement, RIFLE, a diffusion-based framework designed to remove FB while preserving fine details. We propose the flicker-banding prior estimator (FPE) that predicts key banding attributes and injects it into the restoration network. Additionally, Masked Loss (ML) is proposed to concentrate supervision on banded regions without sacrificing global fidelity. To overcome data scarcity, we provide a simulation pipeline that synthesizes FB in the luminance domain with stochastic jitter in banding angle, banding spacing, and banding width. Feathered boundaries and sensor noise are also applied for a more realistic simulation. For evaluation, we collect a paired real-world FB dataset with pixel-aligned banding-free references captured via long exposure. Across quantitative metrics and visual comparisons on our real-world dataset, RIFLE consistently outperforms recent image reconstruction baselines from mild to severe flicker-banding. To the best of our knowledge, it is the first work to research the simulation and removal of FB. Our work establishes a great foundation for subsequent research in both the dataset construction and the removal model design. Our dataset and code will be released soon.

Problem

• Removing flicker-banding artifacts from screen photographs caused by temporal aliasing
• Preserving fine image details while eliminating alternating bright-dark stripes
• Addressing data scarcity through realistic simulation of flicker-banding patterns

Innovation

• Uses latent diffusion framework for flicker-banding removal
• Proposes flicker-banding prior estimator to predict attributes
• Develops simulation pipeline with stochastic jitter parameters