双管齐下：周期性与方向性的二重奏用于连拍闪烁去除
It Takes Two: A Duet of Periodicity and Directionality for Burst Flicker Removal
针对短曝光连拍中的结构化闪烁伪影，提出基于Transformer的复原框架，利用相位相关融合帧间特征、自相关捕捉帧内结构规律、小波域方向注意力定位伪影，为特定退化模式的定制化复原提供了可复用的设计思路。
原文依据 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).
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论闪烁伪影源于不稳定的光照和逐行曝光不一致，在短曝光摄影中构成重大挑战，严重降低图像质量。与噪声、低光照等典型伪影不同，闪烁是一种具有特定时空模式的结构化退化，当前通用复原框架未考虑这些模式，导致闪烁抑制效果不佳并产生鬼影伪影。本文揭示闪烁伪影具有两个内在特性——周期性和方向性，并提出Flickerformer，一种基于Transformer的架构，能有效去除闪烁而不引入鬼影。具体而言，Flickerformer包含三个关键组件：基于相位的融合模块（PFM）、自相关前馈网络（AFFN）和基于小波的方向注意力模块（WDAM）。基于周期性，PFM执行帧间相位相关以自适应聚合连拍特征，而AFFN通过自相关利用帧内结构规律，共同增强网络感知空间重复模式的能力。此外，受闪烁伪影方向性启发，WDAM利用小波域中的高频变化引导低频暗区复原，实现闪烁伪影的精确定位。大量实验表明，Flickerformer在定量指标和视觉质量上均优于最优方法。源代码见https://github.com/qulishen/Flickerformer。
英文原文摘要 1618 字符
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.