论文标题
NERF-SLAM：实时密集的单眼大满贯与神经辐射场
NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields
论文作者
论文摘要
我们提出了一种新颖的几何和光度3D映射管道，以从单眼图像中进行准确和实时场景重建。为了实现这一目标，我们利用了密集的单眼大满贯和实时层次体积神经光辐射场的最新进展。我们的见解是，密集的单眼大满贯提供了正确的信息，可通过提供准确的姿势估计和深度图和相关的不确定性来实时拟合现场的神经辐射场。凭借我们提出的基于不确定性的深度损失，我们不仅达到了良好的光度准确性，而且还达到了良好的几何精度。实际上，我们提出的管道比竞争方法（PSNR好高达179％，L1深度高达179％）可以实现更好的几何和光度准确性，同时仅实时工作，并且仅使用单眼图像。
We propose a novel geometric and photometric 3D mapping pipeline for accurate and real-time scene reconstruction from monocular images. To achieve this, we leverage recent advances in dense monocular SLAM and real-time hierarchical volumetric neural radiance fields. Our insight is that dense monocular SLAM provides the right information to fit a neural radiance field of the scene in real-time, by providing accurate pose estimates and depth-maps with associated uncertainty. With our proposed uncertainty-based depth loss, we achieve not only good photometric accuracy, but also great geometric accuracy. In fact, our proposed pipeline achieves better geometric and photometric accuracy than competing approaches (up to 179% better PSNR and 86% better L1 depth), while working in real-time and using only monocular images.
