修补
绘画
保护
灵活性(工程)
基础(证据)
计算机科学
艺术
视觉艺术
人工智能
图像(数学)
环境科学
历史
考古
管理
环境规划
经济
出处
期刊:Research Square - Research Square
日期:2024-12-11
标识
DOI:10.21203/rs.3.rs-5568737/v1
摘要
Abstract Conservation of damaged oil paintings requires manual inpainting of losses1,2, leading to months-long treatments of considerable expense: 70% of paintings in institutional collections are locked away from public view in part due to treatment cost3,4. Recent advancements in digital image reconstruction have helped envision treatment results, though without any direct means of achieving them5–8. Here we show the first physically-applied digital restoration of a painting, a highly-damaged oil-on-panel attributed to the Master of the Prado Adoration (MPA) from the late 15th century. In parallel, 5,612 losses spanning 66,205 mm2 and 57,314 colors are infilled with a reversible laminate mask comprising a color-accurate bilayer of printed pigments on polymeric films. To ensure restoration effectiveness, ethical principles in paintings conservation are implemented quantitatively for digital mask construction, a critically-important foundation lacking in current digital restoration literature. The infill process takes 3.5 hours, an estimated 66 times faster than conventional inpainting, with the result closely matching simulation. Our approach grants unprecedented foresight and flexibility to conservators, enabling the restoration of countless damaged paintings deemed unworthy of high conservation budgets.
科研通智能强力驱动
Strongly Powered by AbleSci AI