Contemporary 3D research, particularly in reconstruction and generation, heavily relies on 2D images for inputs or supervision. However, current designs for these 2D-3D mapping are memory-intensive, posing a significant bottleneck for existing methods and hindering new applications. In response, we propose a pair of highly scalable components for 3D neural fields: Lightplane Render and Splatter, which significantly reduce memory usage in 2D-3D mapping. These innovations enable the processing of vastly more and higher resolution images with small memory and computational costs. We demonstrate their utility in various applications, from benefiting single-scene optimization with image-level losses to realizing a versatile pipeline for dramatically scaling 3D reconstruction and generation. Code: \url{https://github.com/facebookresearch/lightplane}.

现代3D研究中，特别是在重建和生成方面，严重依赖于2D图像输入或监督。然而，目前这些2D-3D映射的设计占用大量内存，对现有方法构成了重大瓶颈，并阻碍了新的应用。为此，我们提出了一对高度可扩展的用于3D神经场的组件：Lightplane Render和Splatter，它们显著减少了2D-3D映射中的内存使用量。这些创新使得能够以较小的内存和计算成本处理大量更高分辨率的图像。我们展示了它们在各种应用中的实用性，从从图像级损失中受益的单场景优化到实现用于大幅扩展3D重建和生成的多功能流水线。代码：https://github.com/facebookresearch/lightplane。

Lightplane: 高可扩展的神经三维场组件