论文标题
DERF：分解的辐射场
DeRF: Decomposed Radiance Fields
论文作者
论文摘要
随着神经辐射场（NERF）的出现，神经网络现在可以以愚弄人眼的质量来对3D场景进行新颖的观点。但是，生成这些图像在计算上非常密集，从而限制了它们在实际情况下的适用性。在本文中，我们提出了一种基于能够缓解此问题的空间分解的技术。我们的主要观察结果是，采用更大（更深入和/或更广泛的）网络的回报率降低。因此，我们建议在空间分解场景并为每个分解部分专用较小的网络。当一起工作时，这些网络可以渲染整个场景。无论分解零件的数量多少，这都使我们近乎定义的推理时间。此外，我们表明，为此目的，沃罗诺（Voronoi）空间分解是可取的，因为它与画家的算法相兼容，以进行有效且易于GPU友好的渲染。我们的实验表明，对于实际场景，我们的方法比NERF（具有相同的渲染质量）或PSNR中最高1.0〜db（以相同的推论成本）提高了最高3倍的推理。
With the advent of Neural Radiance Fields (NeRF), neural networks can now render novel views of a 3D scene with quality that fools the human eye. Yet, generating these images is very computationally intensive, limiting their applicability in practical scenarios. In this paper, we propose a technique based on spatial decomposition capable of mitigating this issue. Our key observation is that there are diminishing returns in employing larger (deeper and/or wider) networks. Hence, we propose to spatially decompose a scene and dedicate smaller networks for each decomposed part. When working together, these networks can render the whole scene. This allows us near-constant inference time regardless of the number of decomposed parts. Moreover, we show that a Voronoi spatial decomposition is preferable for this purpose, as it is provably compatible with the Painter's Algorithm for efficient and GPU-friendly rendering. Our experiments show that for real-world scenes, our method provides up to 3x more efficient inference than NeRF (with the same rendering quality), or an improvement of up to 1.0~dB in PSNR (for the same inference cost).
