Deep inverse rendering for high-resolution SVBRDF estimation from an arbitrary number of images
Deep inverse rendering for high-resolution SVBRDF estimation from an arbitrary number of images
复制标题
DOI：
10.1145/3306346.3323042
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Duan Gao;Xiao Li;Yue Dong;P. Peers;Kun Xu;Xin Tong
中科院分区：
文献类型：
--
作者：
Duan Gao;Xiao Li;Yue Dong;P. Peers;Kun Xu;Xin Tong
在本文中，我们提出了一个统一的深度逆渲染框架，用于从任意数量的输入照片（从单张照片到多张照片）估计平面样本的空间变化外观属性。当输入照片未能捕捉到所有反射信息时，估计外观的精度从合理到对于大量输入集的准确不等。我们框架的一个关键区别特征是，它直接针对空间变化外观的潜在嵌入空间中的外观参数进行优化，因此不需要手工制作的启发式方法来规范优化。这种潜在嵌入是通过一个完全卷积自动编码器学习的，该编码器被设计用于规范优化。我们的框架不仅支持任意数量的输入照片，而且支持高分辨率。我们在各种各样的公开可用数据集上展示并评估了我们的深度逆渲染解决方案。
In this paper we present a unified deep inverse rendering framework for estimating the spatially-varying appearance properties of a planar exemplar from an arbitrary number of input photographs, ranging from just a single photograph to many photographs. The precision of the estimated appearance scales from plausible when the input photographs fails to capture all the reflectance information, to accurate for large input sets. A key distinguishing feature of our framework is that it directly optimizes for the appearance parameters in a latent embedded space of spatially-varying appearance, such that no handcrafted heuristics are needed to regularize the optimization. This latent embedding is learned through a fully convolutional auto-encoder that has been designed to regularize the optimization. Our framework not only supports an arbitrary number of input photographs, but also at high resolution. We demonstrate and evaluate our deep inverse rendering solution on a wide variety of publicly available datasets.