Neural Shading Fields for Efficient Facial Inverse Rendering
Neural Shading Fields for Efficient Facial Inverse Rendering
复制标题
用于高效面部逆渲染的神经着色场
DOI：
10.1111/cgf.14943
复制
发表时间：
2023
影响因子：
2.5
通讯作者：
Rainer G
中科院分区：
文献类型：
--
作者：
Rainer G
给出一组未知光照下对象的非结构化照片，3D几何重建相对容易，但反射率估计仍然是一个挑战。这是因为它需要从模糊观测中的反射比中分离出照明。存在利用统计的、数据驱动的先验来输出合理的反射率图的解决方案，即使在受限的单视图、未知的照明设置中也是如此。我们提出了一种不依赖数据驱动先验的低成本逆优化方法，在多视角未知光照的情况下获得高质量的漫反射和镜面反射、反照率和法线贴图。我们引入了紧凑的神经网络，它通过有效地找到面部外观中的相关性来学习给定场景的阴影。我们使用显式漫反射和镜面反射贴图来联合优化网络中场景的隐式全局光照，这些贴图随后可以用于基于物理的渲染。我们对地面真实数据的结果的准确性进行了分析，并证明了我们的反射比图比最先进的深度学习和可区分渲染方法保持了更多的细节和更大的个人认同感。
Given a set of unstructured photographs of a subject under unknown lighting, 3D geometry reconstruction is relatively easy, but reflectance estimation remains a challenge. This is because it requires disentangling lighting from reflectance in the ambiguous observations. Solutions exist leveraging statistical, data‐driven priors to output plausible reflectance maps even in the under‐constrained single‐view, unknown lighting setting. We propose a very low‐cost inverse optimization method that does not rely on data‐driven priors, to obtain high‐quality diffuse and specular, albedo and normal maps in the setting of multi‐view unknown lighting. We introduce compact neural networks that learn the shading of a given scene by efficiently finding correlations in the appearance across the face. We jointly optimize the implicit global illumination of the scene in the networks with explicit diffuse and specular reflectance maps that can subsequently be used for physically‐based rendering. We analyze the veracity of results on ground truth data, and demonstrate that our reflectance maps maintain more detail and greater personal identity than state‐of‐the‐art deep learning and differentiable rendering methods.
DOI：
10.1145/3476576.3476579
发表时间：
2021-06
期刊：
ACM Transactions on Graphics (TOG)
影响因子：
--
作者：
T. Müller;Fabrice Rousselle;J. Nov'ak;A. Keller
通讯作者：
T. Müller;Fabrice Rousselle;J. Nov'ak;A. Keller