论文标题
SuperMVS：高分辨率多视角立体声的非均匀成本量
SuperMVS: Non-Uniform Cost Volume For High-Resolution Multi-View Stereo
论文作者
论文摘要
不同于大多数最新的（SOTA）算法，这些算法使用带有许多假设平面的静态和均匀采样方法来获得精细的深度采样。在本文中，我们提出了一种自由移动的假设平面方法，用于在较宽的深度范围内进行动态和不均匀采样，以构建成本量，这不仅大大降低了平面的数量，而且还可以减少计算成本和提高准确性的精确度，称为非均匀的成本量。我们介绍了SuperMVS网络，以实现具有不均匀成本量的多视图立体声。 SuperMVS是一个具有四个级联阶段的粗到精细框架。它可以输出更高的分辨率和准确的深度图。我们的SuperMV在DTU数据集和坦克\＆temples数据集上以低内存，运行时间较少和更少的飞机来实现SOTA结果。
Different from most state-of-the-art~(SOTA) algorithms that use static and uniform sampling methods with a lot of hypothesis planes to get fine depth sampling. In this paper, we propose a free-moving hypothesis plane method for dynamic and non-uniform sampling in a wide depth range to build the cost volume, which not only greatly reduces the number of planes but also finers sampling, for both of reducing computational cost and improving accuracy, named Non-Uniform Cost Volume. We present the SuperMVS network to implement Multi-View Stereo with Non-Uniform Cost Volume. SuperMVS is a coarse-to-fine framework with four cascade stages. It can output higher resolution and accurate depth map. Our SuperMVS achieves the SOTA results with low memory, low runtime, and fewer planes on the DTU datasets and Tanks \& Temples dataset.
