Multi-View Stereo Network with attention thin volume

10/16/2021
by   Zihang Wan, et al.
0

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.

READ FULL TEXT
research
12/26/2019

Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume

Deep learning has shown to be effective for depth inference in multi-vie...
research
05/28/2022

WT-MVSNet: Window-based Transformers for Multi-view Stereo

Recently, Transformers were shown to enhance the performance of multi-vi...
research
07/25/2022

Cost Volume Pyramid Network with Multi-strategies Range Searching for Multi-view Stereo

Multi-view stereo is an important research task in computer vision while...
research
12/18/2019

Cost Volume Pyramid Based Depth Inference for Multi-View Stereo

We propose a cost volume based neural network for depth inference from m...
research
11/25/2020

Attention Aware Cost Volume Pyramid Based Multi-view Stereo Network for 3D Reconstruction

We present an efficient multi-view stereo (MVS) network for 3D reconstru...
research
08/13/2022

DS-MVSNet: Unsupervised Multi-view Stereo via Depth Synthesis

In recent years, supervised or unsupervised learning-based MVS methods a...
research
11/02/2022

SufrinNet: Toward Sufficient Cross-View Interaction for Stereo Image Enhancement in The Dark

Low-light stereo image enhancement (LLSIE) is a relatively new task to e...

Please sign up or login with your details

Forgot password? Click here to reset