Search Results

Now showing 1 - 2 of 2
  • Item
    Preserving the Khmer Smile: Classifying and Restoring the Faces of Bayon
    (The Eurographics Association, 2011) Lu, Min; Zheng, Bo; Takamatsu, Jun; Nishino, Ko; Ikeuchi, Katsushi; Franco Niccolucci and Matteo Dellepiane and Sebastian Pena Serna and Holly Rushmeier and Luc Van Gool
    The Bayon temple is known for its numerous massive stone faces with serene smiles, often referred to as the 'Khmer Smile.' Many of these sculptures are, however, only partially preserved, making it difficult to see the original appearance of these faces. To restore the Bayon faces, we propose a novel method that builds upon the matrix recovery theory. The method achieves accurate restoration by adopting a two-step shape recovery strategy. Rough restoration and clustering processes are first carried out using the entire database to group similar samples together. Then refined restoration using high resolution data is executed in each cluster to restore higher details while retaining the characteristics of each face. Experimental results demonstrate the effectiveness of our proposed method.
  • Item
    Reassembling Thin Artifacts of Unknown Geometry
    (The Eurographics Association, 2011) Oxholm, Geoffrey; Nishino, Ko; Franco Niccolucci and Matteo Dellepiane and Sebastian Pena Serna and Holly Rushmeier and Luc Van Gool
    We introduce a novel reassembly method for fragmented, thin objects that uses minimal user interaction. Unlike past methods, we do not make any restrictive assumptions about the geometry or texture of the object. To do so, we exploit the geometric and photometric similarity along and across the boundaries of matching fragments, and leverage user feedback to tackle the otherwise ill-posed problem. We begin by encoding the scale variability of each fragment's boundary contour in a multi-channel, 2D representation. Using this multi-channel boundary contour representation, we identify matching sub-contours via 2D partial image alignment. We then align the fragments by minimizing the distance between their adjoining regions while simultaneously ensuring geometric continuity across them. The configuration of the fragments as they are incrementally matched and aligned form a graph structure. By detecting cycles in this graph, we identify subsets of fragments with dependent alignments. We then minimize the error within the subsets to achieve a globally optimal alignment. Using ceramic pottery as the driving example, we demonstrate the accuracy and efficiency of our method on six real-world datasets.