论文标题
改进了辐射场重建的直接体素电网优化
Improved Direct Voxel Grid Optimization for Radiance Fields Reconstruction
论文作者
论文摘要
在此技术报告中，我们改进了基于Pytorch并使用最简单的密集网格表示的DVGO框架（称为DVGOV2）。首先，我们使用CUDA重新实现Pytorch操作的一部分，以2-3x的速度实现。 CUDA扩展将自动及时编译。其次，我们扩展了DVGO，以支持向前的前进和无限的朝内捕获。第三，我们改善了MIP-NERF 360从O（n^2）到O（n）提出的失真损失的时空复杂性。失真损失提高了我们的质量和训练速度。我们有效的实施可以使更多的未来工作从损失中受益。
In this technical report, we improve the DVGO framework (called DVGOv2), which is based on Pytorch and uses the simplest dense grid representation. First, we re-implement part of the Pytorch operations with cuda, achieving 2-3x speedup. The cuda extension is automatically compiled just in time. Second, we extend DVGO to support Forward-facing and Unbounded Inward-facing capturing. Third, we improve the space time complexity of the distortion loss proposed by mip-NeRF 360 from O(N^2) to O(N). The distortion loss improves our quality and training speed. Our efficient implementation could allow more future works to benefit from the loss.
