Museums are sanctuaries of art assets and paintings, offering audiences a once-in-a-lifetime opportunity to immerse themselves in a unique environment. Traditional museums, however, lack certain accessibility and interactive elements. Although the Internet has facilitated access to digital images of these artistic assets and even expanded our reach to vast digital painting libraries, these resources often fail to replicate the dynamic interaction between the artwork and environment. In essence, they tend to lose “surface appearance.”

The advance of photorealistic rendering technologies has opened new doors to replicate these immersive experiences in virtual spaces, such as metaverses or games. This technology enhances the viewer’s experience by offering a more realistic and interactive visual encounter with art. However, the task of modeling these environments, like a museum, still presents considerable challenges due to the manual workloads.

To address these limitations, our study is focused on capturing or generating the surface appearance of artifacts and fine arts. Our objective is to construct a Virtual Museology that accurately represents the museum experience, maintaining the essential elements of interactivity and immersion. This innovative approach includes SVBRDF capturing, material generation, and style transfer.

Multiview SVBRDF Capture from Unified Shape and Illumination

In this study, we propose a stable method for reconstructing spatially varying appearances (SVBRDFs) from multiview images captured under casual lighting conditions. Unlike flat surface capture methods, ours can be applied to surfaces with complex silhouettes. The proposed method takes multiview images as inputs and outputs a unified SVBRDF estimation.


Name Affiliation Web site
Liang Yuan Keio University



  1. Liang Yuan, Issei Fujishiro: “Multiview SVBRDF capture from unified shape and illumination,” Visual Informatics, September 2023, Vo. 7, No. 3, pp. 11-21, ISSN 2468-502X [doi: 10.1016/j.visinf.2023.06.006]. (PDF)


  1. Liang Yuan, Issei Fujishiro: “Multiview SVBRDF capture from unified shape and illumination,” Computer Graphics International 2023, Shanghai, China, August 28–September 1, 2023.


  1. Grant-in-Aid for Scientific Research (A): 21H04916 (2021)

Back to GP team page