Digital Longmen Project: A Free Walking VR System with Image-Based Restoration

Located in China’s ancient capital Luoyang, Longmen Grottoes are one of the finest examples of Buddhist stone carving art. Nowadays, many caves do not have public access due to heritage preservation. In order to let people appreciate these relics, we setup a VR system with smartphones and helmets based on scanned models and textures. Motion capture system is also utilized to make the viewpoint not fixed so that users can walk freely as if in the cave. Moreover, since some sculptures have been heavily damaged, we propose a digital restoration framework to enhance exhibition contents. The framework includes general and detailed restoration from a single old image by shape from shading and landmark driven mesh deformation respectively. In practice, we develop this system for the representative Middle Binyang Cave, with interactions such as gesture recognition exploited to provide satisfactory user experience, which can ease the conflict between tourism and preservation.

[1]  Tim Weyrich,et al.  A system for high-volume acquisition and matching of fresco fragments: reassembling Theran wall paintings , 2008, SIGGRAPH 2008.

[2]  Ping-Sing Tsai,et al.  Shape from Shading: A Survey , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Krzysztof Walczak,et al.  Building Virtual and Augmented Reality museum exhibitions , 2004, Web3D '04.

[4]  Jitendra Malik,et al.  Shape, Illumination, and Reflectance from Shading , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Daisuke Miyazaki,et al.  Digitally Archiving Cultural Objects , 2007 .

[6]  Takeshi Oishi,et al.  Flying Laser Range Sensor for Large-Scale Site-Modeling and Its Applications in Bayon Digital Archival Project , 2008, International Journal of Computer Vision.

[7]  J. Gower Generalized procrustes analysis , 1975 .

[8]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Ying Yang,et al.  ATHENA: Automatic Text Height Extraction for the Analysis of Text Lines in Old Handwritten Manuscripts , 2015, ACM Journal on Computing and Cultural Heritage.

[10]  Yuning Jiang,et al.  Extensive Facial Landmark Localization with Coarse-to-Fine Convolutional Network Cascade , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[11]  Thomas Vetter,et al.  A morphable model for the synthesis of 3D faces , 1999, SIGGRAPH.

[12]  Min H. Kim,et al.  Hyper3D: 3D graphics software for examining cultural artifacts , 2014, JOCCH.

[13]  Holly Rushmeier Computer Graphics Techniques for Capturing and Rendering the Appearance of Aging Materials , 2009 .

[14]  Berthold K. P. Horn,et al.  Shape from shading , 1989 .

[15]  Takeshi Oishi,et al.  Achieving robust alignment for outdoor mixed reality using 3D range data , 2012, VRST '12.

[16]  George Pavlidis,et al.  3D Pottery content-based retrieval based on pose normalisation and segmentation , 2010 .

[17]  Kun Zhou,et al.  Mesh editing with poisson-based gradient field manipulation , 2004, SIGGRAPH 2004.

[18]  Tetsuya Kakuta,et al.  Development and Evaluation of Asuka-Kyo MR Contents with Fast Shading and Shadowing , 2008 .

[19]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[20]  Katsushi Ikeuchi,et al.  Numerical Shape from Shading and Occluding Boundaries , 1981, Artif. Intell..

[21]  Berthold K. P. Horn,et al.  Determining lightness from an image , 1974, Comput. Graph. Image Process..

[22]  Christian Rössl,et al.  Differential coordinates for interactive mesh editing , 2004, Proceedings Shape Modeling Applications, 2004..