Multi-View Stereo Network with attention thin volume
This work addresses the challenge of accurate depth inference from multiple RGB images in computer vision, presenting an incremental improvement over existing methods.
The paper tackled the problem of constructing an efficient cost volume for multi-view stereo depth estimation by introducing a self-attention mechanism and group-wise correlation, resulting in a lightweight and efficient model with reduced memory and computational burden.
We propose an efficient multi-view stereo (MVS) network for infering depth value from multiple RGB images. Recent studies have shown that mapping the geometric relationship in real space to neural network is an essential topic of the MVS problem. Specifically, these methods focus on how to express the correspondence between different views by constructing a nice cost volume. In this paper, we propose a more complete cost volume construction approach based on absorbing previous experience. First of all, we introduce the self-attention mechanism to fully aggregate the dominant information from input images and accurately model the long-range dependency, so as to selectively aggregate reference features. Secondly, we introduce the group-wise correlation to feature aggregation, which greatly reduces the memory and calculation burden. Meanwhile, this method enhances the information interaction between different feature channels. With this approach, a more lightweight and efficient cost volume is constructed. Finally we follow the coarse to fine strategy and refine the depth sampling range scale by scale with the help of uncertainty estimation. We further combine the previous steps to get the attention thin volume. Quantitative and qualitative experiments are presented to demonstrate the performance of our model.