Learning Descriptor, Confidence, and Depth Estimation in Multi-View Stereo

Sungil Choi, Seungryong Kim, Kihong Park, Kwanghoon Sohn; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 276-282

Abstract


Depth estimation from multi-view stereo images is one of the most fundamental and essential tasks in understanding a scene imaginary. In this paper, we propose a machine learning technique based on deep convolutional neural networks (CNNs) for multi-view stereo matching. The proposed method measures the matching cost to extract depth values between two-view stereo images among multi-view stereo images using a deep architecture. Moreover, we present the confidence estimation network for incorporating the cost volumes along the depth hypothesis in multi-view stereo. Experiments show that our estimated depth map from multiple views shows the better performance than the other matching similarity measure on DTU dataset.

Related Material


[pdf]
[bibtex]
@InProceedings{Choi_2018_CVPR_Workshops,
author = {Choi, Sungil and Kim, Seungryong and Park, Kihong and Sohn, Kwanghoon},
title = {Learning Descriptor, Confidence, and Depth Estimation in Multi-View Stereo},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2018}
}