高级检索
高童, 徐昆. 空间可变BRDF贴图的滤波算法[J]. 计算机辅助设计与图形学学报, 2022, 34(9): 1313-1322. DOI: 10.3724/SP.J.1089.2022.19164
引用本文: 高童, 徐昆. 空间可变BRDF贴图的滤波算法[J]. 计算机辅助设计与图形学学报, 2022, 34(9): 1313-1322. DOI: 10.3724/SP.J.1089.2022.19164
Gao Tong, Xu Kun. Spatially Varying BRDF Map Filtering[J]. Journal of Computer-Aided Design & Computer Graphics, 2022, 34(9): 1313-1322. DOI: 10.3724/SP.J.1089.2022.19164
Citation: Gao Tong, Xu Kun. Spatially Varying BRDF Map Filtering[J]. Journal of Computer-Aided Design & Computer Graphics, 2022, 34(9): 1313-1322. DOI: 10.3724/SP.J.1089.2022.19164

空间可变BRDF贴图的滤波算法

Spatially Varying BRDF Map Filtering

  • 摘要: 近年来,实时渲染的真实程度不断上升,空间可变双向反射分布函数(SVBRDF)材质也越来越多地应用在实时渲染中.为了避免走样问题,在渲染前有必要对SVBRDF贴图进行滤波.因此,提出一种考虑SVBRDF纹素各个分量贡献度的综合滤波算法.首先,将每个纹素在拟合时的权重定义为其漫反射率、高光反射率的亮度之和;然后,考查已有vonMises-Fisher(vMF)混合模型,并在拟合时加入权重分量;最后,通过启发式地选择k中心算法的初始值,提出一种改进的自底向上多级SVBRDF纹理计算方法.为测试算法效果,手工设计了4套具有不同微观法向分布的SVBRDF贴图.实验结果表明,在渲染这种复杂材质时,所提算法的RMSE值比参考算法降低25.5%;在改变拟合叶片数量时,所提算法仅用2个vMF叶片就可以取得比已有算法用4个叶片更好的渲染结果.

     

    Abstract: In recent years,the use of spatially varying bidirectional reflectance distribution function(SVBRDF)textures has been steadily increasing in real-time rendering.To reduce aliasing,it is necessary to prefilter SVBRDF textures before rendering.A comprehensive filtering algorithm is proposed that considers the contribution of each component of the SVBRDF texels.First,the weight of each texel is defined as the sum of the luminance of its diffuse albedo and specular albedo.Next,the model of mixture of von Mises-Fisher(vMF)is examined and weighting mechanism is added to it.Finally,by heuristically choosing the initial values for the k-means algorithm,an improved method for calculating SVBRDF Mipmap in a bottom-up fashion is proposed.To evaluate the algorithm,4 SVBRDF materials with different microscopic normal distributions are crafted by hand.When rendering complex SVBRDF materials,the proposed method could achieve an RMSE value 25.5%lower than that of the reference algorithm.When changing the number of fitted lobes,the proposed algorithm can obtain a better result with 2 vMF lobes than previous methods with 4 lobes.

     

/

返回文章
返回