基于密度估计与聚类的混合空间加速结构  

Hybrid Spatial Acceleration Structure Based on Density Estimation and Clustering

作　　者：郭昀辉 何晓曦[1] 胡梁 任和 陈锦伟 GUO Yunhui;HE Xiaoxi;HU Liang;REN He;CHEN Jinwei(College of Software Engineering,Chengdu University of Information Technology,Chengdu 610225,China)

机构地区：[1]成都信息工程大学软件工程学院,四川成都610225

出　　处：《软件导刊》2025年第2期121-128,共8页Software Guide

摘　　要：为解决在密度分布不均的复杂体素场景中构建的空间加速结构时间长、质量较差等问题,提出一种基于密度估计与聚类的混合空间加速结构。首先,在传统边界包围盒层次结构的基础上,通过改进的核密度估计方法为离散的体素数据构造连续的密度环境;其次,根据核密度估计函数的一、二阶偏导方程和聚类结果,以确定体素空间中的高密度区域;最后,提出一种自适应跳跃洪泛算法在这些区域中构建相应的有向距离场,作为加速结构树的叶子节点,计算过程均由GPU实现以满足复杂场景的大规模并行计算需求。结果表明,所提算法在体素密度分布不均的复杂场景中,构建的空间加速结构树时间较短、搜索效率更优,可有效提升光线追踪的渲染速度。To solve the problem of long construction time and poor quality of spatially accelerated structures constructed in complex voxel scenarios with uneven density distribution,a hybrid spatially accelerated structure based on density estimation and clustering is proposed.Based on the traditional bounding volume hierarchy,a continuous density environment is constructed for discrete voxel data through an improved kernel density estimation method.The high-density regions in the voxel space are determined based on the first-and second-order partial derivative equations of the kernel density estimation function and the clustering results.An adaptive jump flooding algorithm is proposed in this paper to construct the corresponding signed distance fields in these regions as leaf nodes of the accelerated structured tree.All computational processes are handed over to GPUs for implementation,thus meeting the demand for massively parallel computation in complex scenarios.The results show that the construction time of the spatially accelerated structure tree supported by this algorithm is significantly shortened and the search efficiency is improved in complex scenes with uneven voxel density distribution,which implies that this method can effectively improve the rendering speed of ray tracing.

关 键 词：空间加速结构 核密度估计 基于密度的聚类 有向距离场 光线追踪 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]