AI Network Learns to Spot Faint Damage on Ancient Murals
Researchers have developed MuHP-DLNet, a multi-stage deep learning network with a damage-aware dynamic loss that improves the detection and segmentation ...
Researchers have developed MuHP-DLNet, a multi-stage deep learning network with a damage-aware dynamic loss that improves the detection and segmentation ...
Researchers have built a structural parameterisation framework that captures Mongolian ornamental patterns across different material carriers and validated it through ...
A multidimensional computer vision framework measuring aspect ratio, ink coverage, and fractal boundary complexity finds that the disputed Song Dynasty ...
Non-destructive microscopy, chemical analysis and 3D surface measurements indicate that a severely deformed 1834 William IV silver sixpence was most ...
A new study of 18,000-year-old mammoth-ivory Venus figurines from Mizyn in Ukraine shows that Ice Age carvers deliberately incorporated the ...
A differential bioarchaeological assessment of a stone object found inside the mouth of a Warring States-period Qin burial in China ...
A multi-analytical study of early Western Han dynasty lacquer boxes from Chongqing, China, reveals the materials and craftsmanship behind ancient ...
Researchers used micro-laser-induced breakdown spectroscopy to identify pigments and map paint layer thicknesses in the ancient murals of Dunhuang's Mogao ...
A new study in Heritage models light-induced discoloration across forty wood species used in artistic objects, combining colorimetry and chemometrics ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine