Learning-based multi-view stereo (MVS) methods have demonstrated promising
results. However, very few existing networks explicitly take the pixel-wise
visibility into consideration, resulting in erroneous cost aggregation from
occluded pixels. In this paper, we explicitly infer and integrate the
pixel-wise occlusion information in the MVS network via the matching
uncertainty estimation. The pair-wise uncertainty map is jointly inferred with
the pair-wise depth map, which is further used as weighting guidance during the
multi-view cost volume fusion. As such, the adverse influence of occluded
pixels is suppressed in the cost fusion. The proposed framework Vis-MVSNet
significantly improves depth accuracies in the scenes with severe occlusion.
Extensive experiments are performed on DTU, BlendedMVS, and Tanks and Temples
datasets to justify the effectiveness of the proposed framework.

本文基于学习的多视角立体 (MVS) 方法，采用匹配不确定性估计，将像素级遮挡信息显式地推理和集成到 MVS 网络中，从而抑制像素遮挡对成本聚合的不利影响，提高了 Vis-MVSNet 算法在严重遮挡场景中的深度精度。在 DTU、BlendedMVS 和 Tanks and Temples 数据集上进行了广泛实验证明了所提出算法的有效性。