Geometric Based Structure Propagation and Texture Matching for 3D Texture Completion

Abstract

This paper proposes a novel method to complete the missing appearance of mesh surfaces through structure propagation and texture matching. In advance, the appearance on surfaces is divided into structure and texture components. First, the missing structures are predicted through structure propagation. The structure propagation is guided by surfaces geometric features by using 3D tensor voting and crest line detection. Then, with the guidance of predicted structures, the optimal local sample patches are matched to inpaint the missing texture. Finally, the completed result is obtained by mapping the optimal patches to the missing texture regions on surface. We acquire convincing completion results as shown in the experiments and comparisons.

A Search Method for Reassembling the Elements of a Broken 2D Object

“…1). They have many variations, depending on: (i) the relevance and applicability of texture data, (ii) whether the purpose is to arrange the elements of an object or fragments of texture on the complete geometry [2] and (iii) the adopted projection of objects and the space in which they are checked (2D and 3D). The texture data can be used to rebuild the geometry or to complete the texture itself.…”