DeRF：分解辐射场
DeRF: Decomposed Radiance Fields
摘要：
随着神经辐射场（NeRF）的出现，神经网络现在可以渲染3D场景的新视图，其质量可以欺骗人眼。然而，生成这些图像是非常计算密集型的，限制了它们在实际场景中的适用性。在本文中，我们提出了一种基于空间分解的技术，能够缓解这个问题。我们的主要观察结果是，使用更大（更深和/或更广）的网络会带来收益递减。因此，我们建议对场景进行空间分解，并为每个分解部分专用更小的网络。当这些网络一起工作时，它们可以渲染整个场景。这使得我们几乎恒定的推理时间，而不管分解部分的数量。此外，我们表明，Voronoi空间分解是最好的为此目的，因为它是可证明兼容的高效和GPU友好的渲染与画家的算法。我们的实验表明，对于真实世界的场景，我们的方法提供了高达3倍的效率比NeRF的推理（具有相同的渲染质量），或高达1.0 dB的提高PSNR（相同的推理成本）。
英文摘要：
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).
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。
