Newest papers

Dual-Scale Condition-Shift Editing for Robust Real-World Image Demoiréing

Shiyang Zhou, Haijin Zeng, Congpei Qiu, Zhengcen Li, Ping Chen, Xiangming Wang, Zheng Li, Yongyong Chen, Jingyong Su · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26644 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

屏幕收集的图像的强大重构仍然是具有挑战性的:moiré在频率、颜色和空间支持方面在显示摄像头对和捕捉条件之间有所不同。专门的恢复网络在与这种多样性作斗争时受到训练,特别是当低频率颜色带和高频率带相匹配时。我们介绍了DemoiréEdit,一个内容保留和捕捉条件下的编辑框架,该框架在预先训练的流量匹配编辑器之前对自然图像进行评估,以便进行Demoiré。首先,在低频率图像、感知和研究频率域的恢复损失上,终端监控的培训客观补充了速度。第二,一个双尺寸的条件变化策略在低分辨率下执行全球调节,然后通过

Machine translation (Meta M2M100); the English original follows.

Abstract

Robust demoiréing of screen-recaptured images remains challenging: moiré varies in frequency, color, and spatial support across display-camera pairs and capture conditions. Dedicated restoration networks trained on finite paired data struggle with this diversity, especially when low-frequency color banding and high-frequency stripes co-occur. We present DemoiréEdit, a content-preserving editing framework that adapts the natural-image prior of a pretrained flow-matching editor to demoiréing. First, an endpoint-supervised training objective supplements velocity matching with pixel, perceptual, and frequency-domain restoration losses. Second, a dual-scale condition-shift strategy performs global correction at low resolution, then refines the image at full resolution by shifting the denoising condition from the first-stage output to the original input for detail recovery. We also introduce DailyMoiré130, a benchmark of challenging moiré in everyday screen photography, comprising 130 smartphone captures across diverse displays with low-frequency color banding, fine high-frequency stripes, and mixed-frequency interference. On the challenging DailyMoiré130 benchmark, our method achieves the lowest residual moiré area and receives 71.3% overall-quality preference in a blind Best-of-7 study with 31 participants. We also evaluate on paired FHDMi/UHDM, reducing residual moiré confidence by 47.1%/9.3% and increasing MUSIQ by 4.3%/2.0% over the best baseline for each metric.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Artificial intelligence, Computer science, Residual, Computer vision, Benchmark (surveying), Image editing

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange