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

Korean

디스플레이 카메라 쌍 및 캡처 조건을 통한 주파수, 색상 및 공간 지원에 따라 moiré가 다양합니다. 이 다양성과 결합된 최종 데이터 투쟁에 훈련 된 전용 복구 네트워크는 특히 낮은 주파수 색상 밴딩과 높은 주파수 스트립이 함께 발생할 때 어려움을 겪습니다. 우리는 DemoiréEdit를 소개합니다. 첫째, 최종 주파수 색상 밴딩과 높은 주파수 스트립의 속도와 일치하는 속도를 보완합니다. 둘째, 이중 규모의 기본 조건 변화 전략은 낮은 해상도에 글로벌 교정을 수행 한 다음, 최적화된 전체 해상도에 대한 디스플레이를 다시 정의합니다. 첫 번째 단계 출력에서 높은 주파수에 대한

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