We present an efficient multi-view stereo (MVS) network for 3D reconstruction from multiview images. While previous learning based reconstruction approaches performed quite well, most of them estimate depth maps at a fixed resolution using plane sweep volumes with a fixed depth hypothesis at each plane, which requires densely sampled planes for desired accuracy and therefore is difficult to achieve high resolution depth maps. In this paper we introduce a coarseto-fine depth inference strategy to achieve high resolution depth. This strategy estimates the depth map at coarsest level, while the depth maps at finer levels are considered as the upsampled depth map from previous level with pixel-wise depth residual. Thus, we narrow the depth searching range with priori information from previous level and construct new cost volumes from the pixel-wise depth residual to perform depth map refinement. Then the final depth map could be achieved iteratively since all the parameters are shared between different levels. At each level, the self-attention layer is introduced to the feature extraction block for capturing the long range dependencies for depth inference task, and the cost volume is generated using similarity measurement instead of the variance based methods used in previous work. Experiments were conducted on both the DTU benchmark dataset and recently released BlendedMVS dataset. The results demonstrated that our model could outperform most state-of-the-arts (SOTA) methods. The codebase of this project is at https://github.com/ArthasMil/AACVP-MVSNet.
翻译:我们从多视图图像中为三维重建提供了一个高效的多视图立体(MVS)网络。虽然先前的基于学习的重建方法运行得相当顺利,但大多数以固定分辨率估算深度地图,在每架飞机上使用固定深度假设进行平面扫描量,并在每架飞机上使用固定深度假设进行深度扫描,这需要密集抽样飞机以达到理想的准确性,因此很难达到高分辨率的深度地图。在本文中,我们采用粗度深度深度推断战略,以达到高分辨率深度。本战略在粗度一级估计深度地图,而精度水平的深度地图则被视为比前一级高得多的深度地图,而精度深度残余是像样的深度地图。因此,我们缩小深度搜索范围,利用前一级前一级的信息进行深度测量,并从精度深度深度残留量构建新的成本量,以进行深度改进。然后,最后的深度映射深度地图可以迭接,因为所有参数都是在不同级别之间共享的。在每个级别上,自我感测层被引入特征提取区块,以获取深度依赖的长距离的深度任务,成本量是使用类似度测量的深度测量范围,而产生成本量,而成本量则使用前一级,而不用根据前一级测测测测测测,而采用最偏差的测测测测测测测测测,而使用了前一级的数据。在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级测测测测测测测测测测算中,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在前一级,在试验中,在前方,在前方,在前方,在前方,在前方,在试验中,在前方,在前方,在试验中,在前方,在前方,在前方,在前方,在前方,在前方,在前方,在前