GPU-based Multiple-Choice Scheme for Mesh Simplification

Naimin Koh, Wenjing Zhang, Jianmin Zheng, Yiyu Cai

Abstract: This paper presents a novel GPU-based parallel algorithm to simplify triangular meshes. Existing GPU based methods usually produce simplified meshes with lower quality. This is generally because they put more emphasis on parallelism than mesh quality. After a thorough analysis of the existing methods, we propose a GPU based multiple-choice mechanism, which combines multiple-choice decimation and GPU-based parallel simplification, to balance the mesh quality and computational speed. As a result, our algorithm improves the quality of the simplified meshes and also achieves high speed-up provided by GPU. The experiments and the comparison with the prior art confirm the performance of the proposed algorithm.