用深度学习+遗传算法重构破损拼图，效果优于现有方法。
A Generic Hybrid Framework for 2D Visual Reconstruction
- 用深度网络评估拼图片对整体匹配度，不只看边缘
- 在葡萄牙瓷砖和破损大拼图上达到顶尖准确率
- 适合图像修复、历史文物复原等真实场景应用
本文提出一种通用混合框架，用于解决基于方形非重叠碎片的2D真实世界重建问题（拼图问题，JPP）。该方法融合基于深度学习（DL）的兼容性度量（CM）模型，能整体评估拼图片对的匹配程度，而非仅关注相邻边缘。该CM与优化的遗传算法（GA）求解器结合，利用片对间CM得分迭代搜索全局最优排列。大量实验表明，该框架在多个真实场景中具备良好适应性和鲁棒性。尤其在葡萄牙瓷砖面板及边界侵蚀严重的大型拼图重建任务中，实现了当前最优（SOTA）性能。
原文摘要 · Abstract (English)
This paper presents a versatile hybrid framework for addressing 2D real-world reconstruction tasks formulated as jigsaw puzzle problems (JPPs) with square, non-overlapping pieces. Our approach integrates a deep learning (DL)-based compatibility measure (CM) model that evaluates pairs of puzzle pieces holistically, rather than focusing solely on their adjacent edges as traditionally done. This DL-based CM is paired with an optimized genetic algorithm (GA)-based solver, which iteratively searches for a global optimal arrangement using the pairwise CM scores of the puzzle pieces. Extensive experimental results highlight the framework's adaptability and robustness across multiple real-world domains. Notably, our unique hybrid methodology achieves state-of-the-art (SOTA) results in reconstructing Portuguese tile panels and large degraded puzzles with eroded boundaries.
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。