Shumeng Dai presents poster at ICRI 24
Congratulations to Shumeng Dai, whose poster “Gen AI for Virtual Restoration of Chinese Paintings: Insights into Possibilities for Conservation” was accepted to the 2024 Institute of
Conservator-Restorers in Ireland Conference. The poster is co-authored with Kate Hennessy and Steve DiPaola.
Abstract:
Chinese painting restoration is facing several challenges, such as the high risk involved in inpainting, the decreasing number of conservators skilled in detailed inpainting, and a conflict between the conservation principles of minimal intervention, recognizability, and reversibility (Muñoz-Viñas, 2012), and the traditional pursuit of completeness and perfection in Chinese painting conservation (Gao & Jones, 2021; Liszewska, 2015). AI is increasingly being applied in fields related to art, including conservation. For example, AI was recently used to decipher the text of the unopened Herculaneum scrolls (Sample, 2024). Generative AI (GenAI), a technology that uses machine learning to analyze image and text data and generate new images, is widely used in areas like animation and artistic design. Can this technology be applied to virtually restore damaged Chinese paintings? This study will explore the potential of using Gen AI for virtual restoration in the field of Chinese painting conservation.
