论文标题
成本量的金字塔网络，具有多策略范围搜索多视图立体声
Cost Volume Pyramid Network with Multi-strategies Range Searching for Multi-view Stereo
论文作者
论文摘要
多视图立体声是计算机视觉中的重要研究任务，同时仍然保持挑战。近年来，基于深度学习的方法在这项任务上表现出卓越的性能。基于金字塔网络的成本量基于基于金字塔网络的方法，以粗到精细的方式逐步完善深度图，在消耗更少的记忆力的同时，产生了令人鼓舞的结果。但是，这些方法无法完全考虑每个阶段成本量的特征，从而为每个成本量阶段采用类似的范围搜索策略。在这项工作中，我们提出了一个基于多视图立体声的不同搜索策略的新颖成本量的网络。通过选择不同的深度范围采样策略并应用自适应单峰滤波，我们能够在低分辨率阶段获得更准确的深度估计，并迭代地逐步映射深度映射到任意分辨率。我们在DTU和BlendenDMVS数据集上进行了广泛的实验，结果表明，我们的方法的表现优于大多数最新方法。
Multi-view stereo is an important research task in computer vision while still keeping challenging. In recent years, deep learning-based methods have shown superior performance on this task. Cost volume pyramid network-based methods which progressively refine depth map in coarse-to-fine manner, have yielded promising results while consuming less memory. However, these methods fail to take fully consideration of the characteristics of the cost volumes in each stage, leading to adopt similar range search strategies for each cost volume stage. In this work, we present a novel cost volume pyramid based network with different searching strategies for multi-view stereo. By choosing different depth range sampling strategies and applying adaptive unimodal filtering, we are able to obtain more accurate depth estimation in low resolution stages and iteratively upsample depth map to arbitrary resolution. We conducted extensive experiments on both DTU and BlendedMVS datasets, and results show that our method outperforms most state-of-the-art methods.
