The core of Multi-view Stereo(MVS) is the matching process among reference
and source pixels. Cost aggregation plays a significant role in this process,
while previous methods focus on handling it via CNNs. This may inherit the
natural limitation of CNNs that fail to discriminate repetitive or incorrect
matches due to limited local receptive fields. To handle the issue, we aim to
involve Transformer into cost aggregation. However, another problem may occur
due to the quadratically growing computational complexity caused by
Transformer, resulting in memory overflow and inference latency. In this paper,
we overcome these limits with an efficient Transformer-based cost aggregation
network, namely CostFormer. The Residual Depth-Aware Cost Transformer(RDACT) is
proposed to aggregate long-range features on cost volume via self-attention
mechanisms along the depth and spatial dimensions. Furthermore, Residual
Regression Transformer(RRT) is proposed to enhance spatial attention. The
proposed method is a universal plug-in to improve learning-based MVS methods.

本论文提出了一种名为 CostFormer 的高效 Transformer-based 成本聚合网络，其中 Residual Depth-Aware Cost Transformer（RDACT）用于通过沿深度和空间维度的自我注意机制聚合成本体上的长程特征，而 Residual Regression Transformer（RRT）则用于增强空间关注。