Adaptive Surface Texture Synthesis Using Round-Shaped Neighbourhoods

Abstract

This paper presents a novel surface texture synthesis method, which is capable of producing high-quality results by performing the synthesis within an effective multi-resolution scheme using an adaptive texture similarity metric. Compared with related works, our method allows us to directly carry out multi-resolution synthesis without involving complicated operations such as mesh hierarchy and partitioning on the target surface. Also, the adaptive similarity metric focuses on measuring texture properties at different scales ranging from local to global, allowing for consistency within differently-sized texture structures. Further, with the introduced round shaped neighbourhoods, we can save considerable amount of computation for the surface texture synthesis over variable texture directions. Experimental results are provided and comparisons are made against other latest works.