An Inverse Procedural Modeling Pipeline for SVBRDF Maps
An Inverse Procedural Modeling Pipeline for SVBRDF Maps
复制标题
SVBRDF 地图的逆向过程建模流程
DOI：
10.1145/3502431
复制
发表时间：
2022
影响因子：
6.2
通讯作者：
Rushmeier, Holly
中科院分区：
文献类型：
--
作者：
Hu, Yiwei;He, Chengan;Deschaintre, Valentin;Dorsey, Julie;Rushmeier, Holly
程序建模现已成为工业中材料建模的事实上的标准。与捕获材料的基于像素的表示不同，程序模型可以编辑并轻松扩展。在本文中，我们提出了一种用于通用材料程序化的半自动管道。给定表示为像素图集的空间变化双向反射分布函数 (SVBRDF)，我们的管道将它们分解为子材质树，其空间分布由其关联的掩模图编码。在我们新的频谱感知材质抠图和基于实例的分解方法的驱动下，材质贴图的半自动分解按层次进行。每个分解的子材质都通过新颖的多层噪声模型进行程序化，以捕获不同尺度的局部变化。这些子材质的空间分布通过恢复点处理纹理基本函数 (PPTBF) 的示例逆合成方法或通过随机采样进行建模。为了重建程序材质贴图，我们提出了一种基于可微分渲染的优化，将所有生成的程序重新组合在一起，以最大限度地提高程序模型和输入材质像素贴图之间的相似性。我们使用各种合成材料和真实材料评估我们的管道。我们展示了我们的方法处理各种材料类型的能力，消除了之前工作中所需的艺术家设计的材料图的需要[，]。作为完全程序化模型，我们的结果可扩展到任意分辨率，并允许用户对外观进行高级控制。
Procedural modeling is now the de facto standard of material modeling in industry. Procedural models can be edited and are easily extended, unlike pixel-based representations of captured materials. In this article, we present a semi-automatic pipeline for general material proceduralization. Given Spatially Varying Bidirectional Reflectance Distribution Functions (SVBRDFs) represented as sets of pixel maps, our pipeline decomposes them into a tree ofsub-materialswhose spatial distributions are encoded by their associated mask maps. This semi-automatic decomposition of material maps progresses hierarchically, driven by our new spectrum-aware material matting and instance-based decomposition methods. Each decomposed sub-material is proceduralized by a novel multi-layer noise model to capture local variations at different scales. Spatial distributions of these sub-materials are modeled either by a by-example inverse synthesis method recovering Point Process Texture Basis Functions (PPTBF) or via random sampling. To reconstruct procedural material maps, we propose a differentiable rendering-based optimization that recomposes all generated procedures together to maximize the similarity between our procedural models and the input material pixel maps. We evaluate our pipeline on a variety of synthetic and real materials. We demonstrate our method’s capacity to process a wide range of material types, eliminating the need for artist designed material graphs required in previous work [, ]. As fully procedural models, our results expand to arbitrary resolution and enable high-level user control of appearance.
登录
查看更多内容
材质GAN
影响因子：
6.2
作者：
Yu Guo;Cameron Smith;Milovs Havsan;Kalyan Sunkavalli;Shuang Zhao
通讯作者：
Shuang Zhao
DOI：
10.1145/3478513.3480507
发表时间：
2021-02
期刊：
ACM Transactions on Graphics (TOG)
影响因子：
--
作者：
P. Henzler;V. Deschaintre;N. Mitra;Tobias Ritschel
通讯作者：
P. Henzler;V. Deschaintre;N. Mitra;Tobias Ritschel
DOI：
10.1109/iccv.2019.00459
发表时间：
2019-10
期刊：
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
影响因子：
--
作者：
Assaf Shocher;Shai Bagon;Phillip Isola;M. Irani
通讯作者：
Assaf Shocher;Shai Bagon;Phillip Isola;M. Irani
影响因子：
2.5
作者：
Pascal Guehl;Rémi Allègre;J. Dischler;Bedrich Benes;Eric Galin
通讯作者：
Pascal Guehl;Rémi Allègre;J. Dischler;Bedrich Benes;Eric Galin
影响因子：
2.5
作者：
Guarnera, D.;Guarnera, G. C.;Glencross, M.
通讯作者：
Glencross, M.