Abstract | ||
---|---|---|
Cultural relics are often damaged and incomplete due to various reasons. For the purpose of helping archaeological studies, we present a novel method for simultaneously restoring the original shapes of a group of similar objects. Based on the assumption that similar shapes are approximately linearly correlated, we use a matrix recovery technique to achieve the restoration. In order to represent input shapes in a matrix form, vectorization of each aligned sample is carried out by stacking coordinates of dense corresponding points that are generated by a surface matching scheme using non-rigid deformation. An experiment using 3D scans of facial sculptures from Bayon is conducted, and the result verifies the feasibility and effectiveness of our method. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/978-3-642-22819-3_31 | ACCV Workshops (2) |
Keywords | Field | DocType |
novel method,non-rigid deformation,matrix form,similar object,dense corresponding point,archaeological study,facial sculpture,shape restoration,cultural relic,similar shape,matrix recovery technique | Matrix form,Computer vision,Similarity (geometry),Computer science,Matrix (mathematics),Vectorization (mathematics),Artificial intelligence,Deformation (mechanics),Stacking | Conference |
Volume | ISSN | Citations |
6469 | 0302-9743 | 4 |
PageRank | References | Authors |
0.58 | 15 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Min Lu | 1 | 13 | 1.75 |
Bo Zheng | 2 | 159 | 13.62 |
Jun Takamatsu | 3 | 280 | 51.47 |
Ko Nishino | 4 | 977 | 60.71 |
Katsushi Ikeuchi | 5 | 4651 | 881.49 |