Abstract
Active learning in 3D scene reconstruction has been widely studied, as selecting informative training views is critical for the reconstruction. Recently, Neural Radiance Fields (NeRF) variants have shown performance increases in active 3D reconstruction using image rendering or geometric uncertainty. However, the simultaneous consideration of both uncertainties in selecting informative views remains unexplored, while utilizing different types of uncertainty can reduce the bias that arises in the early training stage with sparse inputs. In this paper, we propose ActiveNeuS, which evaluates candidate views considering both uncertainties. ActiveNeuS provides a way to accumulate image rendering uncertainty while avoiding the bias that the estimated densities can introduce. ActiveNeuS computes the neural implicit surface uncertainty, providing the color uncertainty along with the surface information. It efficiently handles the bias by using the surface information and a grid, enabling the fast selection of diverse viewpoints. Our method outperforms previous works on popular datasets, Blender and DTU, showing that the views selected by ActiveNeuS significantly improve performance.
Abstract (translated)
已经在三维场景重建中广泛研究了积极学习，因为选择有信息的训练视角对于重建至关重要。最近，神经辐射场（NeRF）变体通过图像渲染或几何不确定性在积极三维重建中显示出性能提高。然而，同时考虑选择信息丰富的视角仍然是一个未探索的问题，而利用不同类型的不确定性可以减少在训练早期阶段出现稀疏输入导致的偏差。在本文中，我们提出了ActiveNeuS，它考虑了 both uncertainties（不确定性）。ActiveNeuS通过累积图像渲染不确定性，同时避免估计密度可能引入的偏差。ActiveNeuS计算神经隐性表面不确定性，提供表面信息以及颜色不确定性。它有效地处理偏差，通过表面信息和网格实现观点的快速选择。我们的方法在流行的数据集Blender和DTU上优于以前的工作，表明ActiveNeuS选择的观点显著提高了性能。
URL
https://arxiv.org/abs/2405.02568
