Shiyang Zhou, Haijin Zeng, Congpei Qiu, Zhengcen Li, Ping Chen, Xiangming Wang, Zheng Li, Yongyong Chen · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26644 · open-access PDF
A demonstração robusta de imagens capturadas pelo ecrã continua a ser um desafio: o moiré varia em frequência, cor e suporte espacial em pares de câmeras de tela e condições de captura. Redes de restauração dedicadas treinadas na luta de dados em pares finitos com essa diversidade, especialmente quando ocorrem bandagens de cores de baixa frequência e faixas de alta frequência. Apresentamos o DemoiréEdit, um framework de edição que preserva o conteúdo e que adapta a imagem natural antes de um editor de correspondência de fluxo pré-treinado ao demoiré.
Machine translation (Meta M2M100); the English original follows.
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, a
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26644, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange