cs.CVSep 29, 2025

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

Authors: Libo Zhu, Zihan Zhou, Xiaoyang Liu, Weihang Zhang, Keyu Shi, Yifan Fu, Yulun Zhang

Organizations: Shanghai Jiao Tong University · Central Media Technology Institute, Huawei

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Figures & tables

Figure 1: Overview of RIFLE . The top part shows the datasets we build, including the simulated training dataset (first row) and the real-world testing dataset (second row). The bottom part shows the flicker-banding removal effect on the simulated datasets and real-world scenarios.
Figure 2: Flicker-banding (FB) when filming screens with smartphone cameras. a) Rolling shutter exposure process. b) Typical display brightness modulation (e.g., PWM and scanning refresh). c) Interaction between the camera exposure and screen modulation leads to the banding artifacts. d) Example banding patterns captured from different modern display technologies.
Figure 3: Visual comparison between our simulated flicker-banding and real-world flicker-banding. GT indicates the real-world non-banding images, on which our simulation pipeline is conducted. SIM indicates our simulation FB images, while LQ indicates real-world FB images.
Figure 4: Our flicker-banding simulation pipeline design. a) Stage 1: We generate the general framework based on the basic banding parameters and introduce parameter jitter and feather concatenation for a more realistic transition. b) Stage 2: We overlay the flicker-banding mask on the Y-channel of high-quality (HQ) images and add sensor noise to the reconstructed screen images.
Figure 5: Overview of our model design. a) We propose Banding-Suppressed High-Frequency Prior ( BSHP ), which combines a fine-grained gradient signal with a smooth structural support map to build a compact single-channel prior. b) We adopt a one-step diffusion restoration model and inject BSHP through multi-stage FiLM modulation for degradation-aware feature recalibration. c) We propose a masked loss ( ML ) that emphasizes banded regions while preserving global fidelity.
Figure 6: Visualization of BSHP. Gradient signal GG captures fine transitions but also stripe responses, while repeatability map SS is smoother and provides structural support. Their fusion yields a compact prior PhfP_{\mathrm{hf}} that preserves informative transitions while suppressing unstable banding responses.
MethodsTaskSSIM ↑\uparrowms-SSIM ↑\uparrowLPIPS ↓\downarrowDISTS ↓\downarrowFSIM ↑\uparrowGMSD ↓\downarrow
LQ−-0.62390.67580.30700.19780.79470.2045
        
Notch FilterFiltering0.55620.63130.34110.26000.71960.2110
MAT [ 23 ]Super-resolution0.47470.64790.41140.22430.77660.2003
InvSR [ 24 ]Super-resolution0.61010.68730.38330.21950.80350.2108
Step1X [ 25 ]Image Editing0.61640.67150.35640.20660.79000.2079
Table 1: Quantitative comparison on the real-world FB testing dataset. Except for Notch Filter and FlickerFormer*, all learning-based baselines are trained or finetuned on our simulated data. FlickerFormer* uses the official checkpoint from the original deflickering task, while FlickerFormer denotes the version finetuned on our simulated data. Best results are highlighted in red .
Figure 7: Visual comparison on three representative Real-Flicker cases. RIFLE removes stronger flicker-banding artifacts with cleaner structures and fewer residual stripes than competing baselines.
Figure 8: Visual comparison of RIFLE component ablations on a real-world FB image.
MethodsSSIM ↑\uparrowms-SSIM ↑\uparrowLPIPS ↓\downarrowDISTS ↓\downarrowFSIM ↑\uparrowGMSD ↓\downarrow
       
Baseline0.62010.73700.38080.20480.84430.2085
ML0.66730.78990.25200.16210.88840.1513
BSHP0.66680.79280.25210.15870.89200.1528
ML+BSHP0.68430.83180.22090.14100.92810.1376
Table 2: Ablation study of our proposed components on real-world FB datasets.
Appendix figures & tables24 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 9: Flicker-banding patterns on LED matrix displays with different scanning refresh mechanisms captured under various conditions. b) Thickening of dark stripes, likely due to changes in PWM duty cycle. c-d) Different LED subpixel arrangements. e-f) Atypical banding patterns. h) Complex banding patterns caused by per-block scanning refresh.
Figure 10: Flicker-banding patterns on OLED displays with PWM driving. a) Non-uniform banding in darker areas on an iPhone OLED screen. b) Horizontal gray banding on laptop OLED. c) Extremely bending and color shifts on banding edges.
Figure 11: Flicker-banding patterns on CRT monitors with electron beam scanning. b) Phosphor persistence effect causing trailing artifacts, leaving a ghosting effect.
Figure 12: Flicker-banding patterns on DLP projectors with color wheel and micromirror switching. a-b) Comparison between original and projected images, highlighting the width of color stripes changes with brightness levels. c) Internal components adapted from DMahalko (CC BY-SA 3.0).
Figure 13: The demoiré performance comparison between no FB scene and FB scene.
Figure 14: Additional visual comparison on the remaining Section-1 cases that are not used in Fig. 7 .
Figure 15: The operating system of the User Study.
MethodsRIFLEPiSA-SRMATInvSRStep1XESDNetFlickerFormerNotch Filter
Score/(%)82.414.72.70.0200.10.080
Appendix
Table 3: The results of User Study.
Figure 16: The out-of-distribution test results.
Figure 17: Per-channel visualization of banding-free images (GT) and flicker-banding images (LQ) in RGB color space. Flicker-banding artifacts appear in all three channels of the LQ images.
Figure 18: Per-channel visualization of banding-free images (GT) and flicker-banding images (LQ) in YCbCr\text{Y}\text{C}_{\text{b}}\text{C}_{\text{r}} color space. Dark flicker-banding is concentrated mainly in Y, with substantially weaker effects in the chrominance channels.
Figure 19: Visualization comparison of Y-channel switching effects. Origin shows the original image and Swapped shows the image after exchanging its Y channel with the counterpart.
Figure 20: Visual comparison of RIFLE on synthetic datasets based on RGB/ YCbCr\text{Y}\text{C}_{\text{b}}\text{C}_{\text{r}} color space.
Figure 21: A case where our method leaves residual magenta colored bands.
Figure 25
Figure 24: Our real-world dataset partial visualization (part 1).
Figure 25: Our real-world dataset partial visualization (part 2).
Figure 26: Our simulated dataset based on LSDIR [ 26 ] partial visualization (part 1).
Figure 27: Our simulated dataset based on UHDM [ 8 ] partial visualization (part 2).
ScenePairsLQ exposureLQ ISOGT exposureGT ISO
1151/2500 or 1/500 s360–18001/80 s250
2251/2500 or 1/800 s1000–25001/60 s72
3331/2000 s332–14401/80 s72
4271/2000 s417–24001/80 s72
551/1600 s390–11521/80 s72
Appendix
Table 4: Real-world acquisition settings for the 105 valid image pairs.
MethodBatchIterationsLearning ratePeak memoryTime (h)
Notch FilterN/AN/AN/AN/AN/A
MAT245,0002×10−42\times 10^{-4}23.1 GiB16.2
InvSR44,0005×10−55\times 10^{-5}30.8 GiB20.3
Step1X825,00010−410^{-4}20.5 GiB69.0
ESDNet16186,8752×10−42\times 10^{-4}26.4 GiB50.8
FlickerFormer120,0005×10−55\times 10^{-5}17.7 GiB6.4
Appendix
Table 5: Training settings and costs for the compared checkpoints. N/A denotes a method without training.
MethodParams (M)Memory (GiB)MACs (G)FLOPs (G)Latency (ms)
Notch Filter0N/AN/AN/A58.4
MAT0.6900.4839169337238.5
InvSR983.4023.95207,52115,0422,607.6
Step1X12,511.62039.9809999,1221,998,24424,548.4
ESDNet5.9340.22387014064.1
FlickerFormer4.1553.7336131263169.5
Appendix
Table 6: Inference costs on 512×512512\times 512 inputs. M and G denote 10610^{6} and 10910^{9} . Notch filtering runs on the CPU and is not included in GPU-memory or neural-operation profiling.
MetricLQPiSA-SRRIFLE
OCR-A ↑\uparrow0.95940.87180.8841
Appendix
Table 7: OCR-based text fidelity. Higher OCR-A is better.
MethodSSIM ↑\uparrowMS-SSIM ↑\uparrowLPIPS ↓\downarrowDISTS ↓\downarrowFSIM ↑\uparrowGMSD ↓\downarrowEwarp↓E_{\mathrm{warp}}\downarrow
LQ0.62660.70180.32790.19940.76680.202817.6871
PiSA-SR0.49210.63190.40770.23730.70860.241833.7324
RIFLE0.62270.70740.33970.20310.77090.196520.5202
Appendix
Table 8: Full-dataset video evaluation. EwarpE_{\mathrm{warp}} values are in units of 10−310^{-3} .
More in this topic

Image Enhancement

Image enhancement restores visibility, color, detail, and dynamic range in degraded images for human viewing and downstream vision tasks.

See all 154 papers

Explore similar work

CardsList
Jun 29, 2026

Bricker to BRACE: A Bracket Exposure RAW Dataset and Restoration Model for Flicker-Banding

Flicker-banding (FB), arises from temporal aliasing between a camera's rolling shutter and a display's brightness modulation, degrading screen-captured image readability with color shifts and jagged patterns. Existing single-frame methods with simplified parametric stripe models cannot reliably distinguish these artifacts from genuine texture. To address this, we conduct a systematic analysis of complex FB morphologies and reveal their significant variation across exposure settings, motivating a multi-frame bracketed RAW restoration paradigm. We construct Bricker, a synthetic-real bracketed RAW dataset built via ray-tracing-based physical simulation and automated multi-exposure capture tool. We further propose BRACE: Bracketed RAW Flicker-Banding Removal, a multi-frame restoration model that utilizes frequency-aware banding prior and a multi-scale spatial cross-attention modulator (MSCAM) for cross-exposure spatial fusion. We also introduce the Stripe Frequency Consistency (SFC) metric to evaluate banding removal. Experiments demonstrate state-of-the-art performance on both synthetic and real benchmarks. Our dataset and code are available at: https://github.com/ZZH-qwq/BRACE.

Zihan Zhou, Libo Zhu, Jue Gong +4

Shanghai Jiao Tong University

Image RestorationMulti-Exposure Image Fusion
AskPDF
May 20, 2026

VDFP: Video Deflickering with Flicker-banding Priors

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.

Zhiyi Zhou, Libo Zhu, Zihan Zhou +2

Shanghai Jiao Tong University

Video Restoration
AskPDF
Mar 24, 2026

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

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.

Lishen Qu, Shihao Zhou, Jie Liang +3

Nankai International Advanced Research Institute (SHENZHEN·FUTIAN) · College of Computer Science, Nankai University · OPPO Research Institute +2

Image Restoration
AskPDF