arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.04866cs.CVcs.GR
收藏

RelightableHands:关节手模型的有效神经重照明

RelightableHands: Efficient Neural Relighting of Articulated Hand Models

Carnegie Mellon University(卡内基梅隆大学);Reality Labs Research(Reality Labs研究院)

Shun Iwase, Shunsuke Saito, Tomas Simon, Stephen Lombardi, Timur Bagautdinov, Rohan Joshi, Fabian Prada, Takaaki Shiratori, Yaser Sheikh, Jason Saragih

摘要:

我们提出了第一个神经重新照明的方法,用于渲染高保真个性化的手,可以在新的照明下实时动画。我们的方法采用了教师-学生的框架,其中教师从在光舞台上捕获的图像中学习单点光下的外观,使我们能够在任意照明下合成手,但需要大量的计算。使用由教师模型呈现的图像作为训练数据,有效的学生模型直接实时预测自然光照下的外观。为了实现泛化,我们使用物理启发的照明功能(如可见性,漫反射阴影和镜面反射)对学生模型进行条件化,在粗略的代理几何体上计算,保持较小的计算开销。我们的关键见解是,这些特征与随后的全局光传输效应具有很强的相关性,这足以作为神经重新照明网络的条件数据。此外,与瓶颈照明条件相反,这些特征基于底层几何结构在空间上对齐,从而更好地泛化到不可见的照明和姿势。在我们的实验中,我们证明了我们的照明功能表示的功效,优于基线方法。我们还表明,我们的方法可以以实时速度逼真地重新点燃两个相互作用的手。https://sh8.io/#/relightable_hands

英文摘要:

We present the first neural relighting approach for rendering high-fidelity personalized hands that can be animated in real-time under novel illumination. Our approach adopts a teacher-student framework, where the teacher learns appearance under a single point light from images captured in a light-stage, allowing us to synthesize hands in arbitrary illuminations but with heavy compute. Using images rendered by the teacher model as training data, an efficient student model directly predicts appearance under natural illuminations in real-time. To achieve generalization, we condition the student model with physics-inspired illumination features such as visibility, diffuse shading, and specular reflections computed on a coarse proxy geometry, maintaining a small computational overhead. Our key insight is that these features have strong correlation with subsequent global light transport effects, which proves sufficient as conditioning data for the neural relighting network. Moreover, in contrast to bottleneck illumination conditioning, these features are spatially aligned based on underlying geometry, leading to better generalization to unseen illuminations and poses. In our experiments, we demonstrate the efficacy of our illumination feature representations, outperforming baseline approaches. We also show that our approach can photorealistically relight two interacting hands at real-time speeds. https://sh8.io/#/relightable_hands

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑