It Takes Two: A Duet of Periodicity and Directionality for Burst Flicker Removal

2026-03-24

AI Summary

This work addresses the challenge of structured flicker artifacts in short-exposure photography, which arise from unstable illumination and rolling shutter mechanisms and are notoriously difficult to suppress without introducing ghosting artifacts using existing image restoration methods. To this end, we propose Flickerformer, the first approach that explicitly reveals the dual characteristics of flicker—its periodicity and directionality—and leverages these insights through a novel architecture comprising a Phase Fusion Module (PFM), an Autocorrelation Feed-Forward Network (AFFN), and a Wavelet Directional Attention Module (WDAM). Integrated within a Transformer framework, these components jointly model frequency- and spatial-domain information to achieve high-quality, ghosting-free flicker removal. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches both quantitatively and visually, and the code is publicly released.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Responsible Web: Algorithmic accountability and transparency on the web

Abstract

Flicker artifacts, arising from unstable illumination and row-wise exposure inconsistencies, pose a significant challenge in short-exposure photography, severely degrading image quality. Unlike typical artifacts, e.g., noise and low-light, flicker is a structured degradation with specific spatial-temporal patterns, which are not accounted for in current generic restoration frameworks, leading to suboptimal flicker suppression and ghosting artifacts. In this work, we reveal that flicker artifacts exhibit two intrinsic characteristics, periodicity and directionality, and propose Flickerformer, a transformer-based architecture that effectively removes flicker without introducing ghosting. Specifically, Flickerformer comprises three key components: a phase-based fusion module (PFM), an autocorrelation feed-forward network (AFFN), and a wavelet-based directional attention module (WDAM). Based on the periodicity, PFM performs inter-frame phase correlation to adaptively aggregate burst features, while AFFN exploits intra-frame structural regularities through autocorrelation, jointly enhancing the network's ability to perceive spatially recurring patterns. Moreover, motivated by the directionality of flicker artifacts, WDAM leverages high-frequency variations in the wavelet domain to guide the restoration of low-frequency dark regions, yielding precise localization of flicker artifacts. Extensive experiments demonstrate that Flickerformer outperforms state-of-the-art approaches in both quantitative metrics and visual quality. The source code is available at https://github.com/qulishen/Flickerformer.

Problem

• flicker artifacts
• short-exposure photography
• spatial-temporal patterns
• ghosting artifacts
• image restoration

Innovation

• periodicity
• directionality
• transformer
• burst flicker removal
• wavelet-based attention