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.
翻译:最近,通过直接从稀少的观测中学习神经光亮场,新观点合成工作已经革命了。然而,以这种新模式提供图像的工作进展缓慢,因为精确的量成形方形要求每个射线需要大量样本。以前的工作主要侧重于加快与每个取样点相关的网络评价,例如,将光亮值混入明确的空间数据结构,但这是以模范紧凑为代价的。在本文中,我们提议了一个新的双网络结构,通过学习如何最好地减少所需取样点的数量,取向一个正反向方向。为此,我们将我们的网络分成一个联合培训的取样和阴影网络。我们的培训计划在每条射线上都采用固定的取样位置,并在整个培训过程中逐步引入宽度,以便在低取样点上达到高质量。经过与标数的精细调整后,由此形成的神经神经代表制可以实时完成。我们的实验表明,我们的方法在质量和框架率方面优于同时的紧凑神经代表制,并在高效率的混合式演示中进行。