arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.14645cs.CVcs.GR
收藏

用于实时的视图合成的烘焙神经辐射场

Baking Neural Radiance Fields for Real-Time View Synthesis

Google Research(谷歌研究院)

Peter Hedman, Pratul P. Srinivasan, Ben Mildenhall, Jonathan T. Barron, Paul Debevec

摘要:

诸如神经辐射场(NeRF)的神经体积表示已经成为用于学习从图像表示3D场景的引人注目的技术,其目标是从未观察到的视点渲染场景的照片级真实感图像。然而,NeRF的计算要求对于实时的【形】应用是禁止的:从经过训练的NeRF渲染视图需要查询多层感知器(MLP)数百次。我们提出了一种方法来训练NeRF,然后将其预计算和存储(即“烘焙”)为一种称为稀疏神经辐射网格(SNeRG)的新表示,该表示可以在商品硬件上实时的【形】渲染。为了实现这一点,我们引入了1)NeRF架构的重新表述,以及2)具有学习特征向量的稀疏体素网格表示。生成的场景表示保留了NeRF渲染精细几何细节和视图相关外观的能力,紧凑(每个场景平均不到90 MB),并且可以实时的【形】渲染(在笔记本电脑GPU上每秒超过30帧)。实际屏幕截图显示在我们的视频。

英文摘要:

Neural volumetric representations such as Neural Radiance Fields (NeRF) have emerged as a compelling technique for learning to represent 3D scenes from images with the goal of rendering photorealistic images of the scene from unobserved viewpoints. However, NeRF's computational requirements are prohibitive for real-time applications: rendering views from a trained NeRF requires querying a multilayer perceptron (MLP) hundreds of times per ray. We present a method to train a NeRF, then precompute and store (i.e. "bake") it as a novel representation called a Sparse Neural Radiance Grid (SNeRG) that enables real-time rendering on commodity hardware. To achieve this, we introduce 1) a reformulation of NeRF's architecture, and 2) a sparse voxel grid representation with learned feature vectors. The resulting scene representation retains NeRF's ability to render fine geometric details and view-dependent appearance, is compact (averaging less than 90 MB per scene), and can be rendered in real-time (higher than 30 frames per second on a laptop GPU). Actual screen captures are shown in our video.

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。

↑