arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.10312cs.CVcs.GR
收藏

AdaNeRF:用于神经辐射场实时的绘制的自适应采样

AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fields

Graz University of Technology(格拉茨技术大学);Reality Labs Research(现实实验室研究部门)

Andreas Kurz, Thomas Neff, Zhaoyang Lv, Michael Zollhöfer, Markus Steinberger

摘要:

通过直接从稀疏观测中学习神经辐射场,新颖的视图合成最近发生了革命性的变化。然而,由于体渲染方程的精确求积需要针对每条射线的大量样本,因此使用这种新范例绘制图像是缓慢的。以前的工作主要集中在加速与每个样本点相关联的网络评估,例如,通过将辐射值高速缓存到显式空间数据结构中,但是这是以模型紧凑性为代价的。在本文中,我们提出了一种新的双网络架构,通过学习如何最好地减少所需的样本点的数量,采取正交方向。为此,我们将我们的网络分成一个采样和着色网络,它们是联合训练的。我们的训练方案沿每条射线采用固定的样本位置,并在整个训练过程中逐步引入稀疏性,即使在低样本数下也能实现高质量。在对目标样本数进行微调之后,可以实时的【形】呈现所得到的紧凑神经表示。我们的实验表明,我们的方法优于并发紧凑的神经表示的质量和帧速率,并表现出与高效的混合表示。代码和补充材料可在https://thomasneff.github.io/adanerf上获得。

英文摘要:

Novel view synthesis has recently been revolutionized by learning neural radiance fields directly from sparse observations. However, rendering images with this new paradigm is slow due to the fact that an accurate quadrature of the volume rendering equation requires a large number of samples for each ray. Previous work has mainly focused on speeding up the network evaluations that are associated with each sample point, e.g., via caching of radiance values into explicit spatial data structures, but this comes at the expense of model compactness. In this paper, we propose a novel dual-network architecture that takes an orthogonal direction by learning how to best reduce the number of required sample points. To this end, we split our network into a sampling and shading network that are jointly trained. Our training scheme employs fixed sample positions along each ray, and incrementally introduces sparsity throughout training to achieve high quality even at low sample counts. After fine-tuning with the target number of samples, the resulting compact neural representation can be rendered in real-time. Our experiments demonstrate that our approach outperforms concurrent compact neural representations in terms of quality and frame rate and performs on par with highly efficient hybrid representations. Code and supplementary material is available at https://thomasneff.github.io/adanerf.

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。

↑