论文标题
深层贴片MV，具有学识渊博的斑块共晶格，几何一致性和自适应像素采样
Deep PatchMatch MVS with Learned Patch Coplanarity, Geometric Consistency and Adaptive Pixel Sampling
论文作者
论文摘要
多视图立体声（MV）的最新工作结合了可学习的光度评分和基于贴片的优化的正则化，以实现深度，正常和可见性的稳健像素估计。但是，对于具有稀疏视图的大型场景，基于非学习的方法的表现仍然胜过，部分原因是使用几何一致性限制和在高分辨率下在许多视图上进行优化的能力。在本文中，我们以学习贴片的共同性来提高基于学习的方法来提高光度分数，并通过学习可以与再投影误差相结合的缩放光度成本来鼓励几何一致性。我们还提出了一种自适应像素采样策略，以供候选传播，以减少记忆，从而使更大的分辨率培训具有更多的视图和更大的编码器。这些修改导致具有挑战性的ETH3D基准的准确性和完整性的增长6-15％，导致F1性能高于广泛使用的最新非学习方法ACMM和ACMP。
Recent work in multi-view stereo (MVS) combines learnable photometric scores and regularization with PatchMatch-based optimization to achieve robust pixelwise estimates of depth, normals, and visibility. However, non-learning based methods still outperform for large scenes with sparse views, in part due to use of geometric consistency constraints and ability to optimize over many views at high resolution. In this paper, we build on learning-based approaches to improve photometric scores by learning patch coplanarity and encourage geometric consistency by learning a scaled photometric cost that can be combined with reprojection error. We also propose an adaptive pixel sampling strategy for candidate propagation that reduces memory to enable training on larger resolution with more views and a larger encoder. These modifications lead to 6-15% gains in accuracy and completeness on the challenging ETH3D benchmark, resulting in higher F1 performance than the widely used state-of-the-art non-learning approaches ACMM and ACMP.
