提出通用去摩尔纹方法，用自动生成数据提升模型泛化能力
UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis
- 通过自动合成大量高质量摩尔纹图像，解决训练数据不足问题
- 在多个未知摩尔纹域上表现优异，显著提升模型泛化性
- 适合需要跨域鲁棒性的实际图像修复场景
图像去摩尔纹是图像复原中最具挑战性的任务之一，主要源于摩尔纹模式的不可预测性和各向异性。受训练数据数量和多样性的限制，现有方法往往过度拟合单一摩尔纹域，导致在新域上性能下降，难以满足真实应用的鲁棒性需求。本文提出通用去摩尔纹方案UniDemoiré，具备卓越的泛化能力。关键创新在于设计了高效的数据生成与合成方法，可自动生成海量高质量摩尔纹图像，用于训练通用去摩尔纹模型。大量实验表明，该方法在广义去摩尔纹任务中达到领先性能，展现出广阔的应用潜力。
原文摘要 · Abstract (English)
Image demoiréing poses one of the most formidable challenges in image restoration, primarily due to the unpredictable and anisotropic nature of moiré patterns. Limited by the quantity and diversity of training data, current methods tend to overfit to a single moiré domain, resulting in performance degradation for new domains and restricting their robustness in real-world applications. In this paper, we propose a universal image demoiréing solution, UniDemoiré, which has superior generalization capability. Notably, we propose innovative and effective data generation and synthesis methods that can automatically provide vast high-quality moiré images to train a universal demoiréing model. Our extensive experiments demonstrate the cutting-edge performance and broad potential of our approach for generalized image demoiréing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。