基于外存的场景加速数据结构快速构建算法  

Fast construction algorithm of out-of-core based scene acceleration data structure

作　　者：刘森[1] 吴志红[1] 

机构地区：[1]四川大学计算机学院视觉合成图形图像技术国防重点学科实验室,成都610065

出　　处：《四川大学学报（自然科学版）》2016年第2期289-294,共6页Journal of Sichuan University(Natural Science Edition)

基　　金：国家科技支撑计划(2012BAH62F03);国家自然科学基金(61472261);863计划(2015AA016405)

摘　　要：大规模场景的绘制问题一直以来都是图形学中的重要研究课题之一.其难点在于场景本身占用内存资源多;其次图形绘制过程计算量巨大.因此本文以大规模场景为研究对象,设计了一种多级层次包围盒用于管理场景数据,并利用GPU的并行计算能力,加速多级层次包围盒的构建,提高绘制效率.本文算法的贡献在于,利用莫顿编码将场景分块问题转化为图元排序问题,从而快速完成场景分块,并以此构造多级层次包围盒;同时,针对多级层次包围盒,使用分段遍历策略,以初始阶段的遍历结果进行I/O调度,有效地减少了遍历时间.实验结果证明了该算法的正确性与可靠性,与CPU的遍历效率相比,提高10x以上.Large-scale scene＇s rendering is one of the major research topics in computer graphics.First,it needs lots of memory resource;second,rendering process requires a great amount of computation.This paper focuses on large-scale scene and proposes a novel algorithm which named Multi-Level Bounding Volume Hierarchies to manage scene data,and then using GPU to accelerate construction and traversal process.The algorithm has two contributions.First using spatial Morton codes to sort triangle primitives,then chapping scene into blocks and constructing MLBVH;at the same time,the traverse efficient have significantly improved by using a two phase traverse tactics,which using the first stage result to control the second stage traverse.Finally,the authors have done some experiments to prove the algorithm correctness and reliability.Traverse efficiency has improved 10 xcompared with CPU.

关 键 词：大规模场景 GPU 遍历策略 多级层次包围盒 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]