An Atlas-based Approach for Appearance-aware Virtual 3D Restoration and Simulation of Fading in Fugitive Textiles

Simulating the discoloration of cultural heritage garments provides valuable insights into their history and supports their preservation. For this purpose, digital methods provide innovative solutions that can leverage the realism of aging processes without causing damage to the artifact. In this work, we propose a method to render color changes in two fugitive textiles housed at the Victoria and Albert Museum. We use a combination of novel atlas-based material segmentation and color restoration approaches to transfer appearance from textile mockups to the 3D models of the garments. The fading effects are induced with accelerated aging on mockups that are chemical proxies of the historic garments, with their aging monitored colorimetrically and spectrally, and their appearance measured with a total appearance capture device. Our proposed approach generates a colour-cue-based segmentation map over a 3D surface, followed by appearance transfer to segmented regions from mockups and fading simulations from spectral unmixing, along with appearance-aware restoration optimized using a reference image. By facilitating appearance-aware fading simulation in virtual 3D models in an interactive app, our approach supports a realistic visualization of colour change in the past and the future. We evaluate our method on two heritage garments - a 20th-century kimono and a 19th-century Victorian dress featuring different fabrics (silk and cotton) and dyed with natural and synthetic materials. In accordance with data collected through scientific analysis measurements, the proposed method effectively transfers a visual appearance that is both plausible and consistent with the data, providing both specialists and lay audiences with a range of fading simulations to support interpretation and restoration decisions.