GPU-based interactive near-regular texture synthesis for digital human models.

Abstract

Near-regular texture is a common feature for both nature scene and 3D human models. However, traditional texture synthesis has only been able to produce a single result. This study proposes a parallel, and interactive, method for the texture synthesis of irregular appearance in 3D human models. The new method includes two major procedures: (1) iterative edge extraction and processing, and (2) parallel texture synthesis, which generates a texture with higher quality. In this paper, the effectiveness of near-regular texture synthesis algorithm is demonstrated experimentally.