Deep Learning for Multi-View Stereo via Plane Sweep: A Survey
It is a survey paper, so it is incremental and synthesizes existing work for researchers in computer vision and 3D reconstruction.
This paper reviews recent progress in deep learning methods for Multi-view Stereo (MVS), a key task in 3D reconstruction, and provides comparative results on public datasets with insights for future research.
3D reconstruction has lately attracted increasing attention due to its wide application in many areas, such as autonomous driving, robotics and virtual reality. As a dominant technique in artificial intelligence, deep learning has been successfully adopted to solve various computer vision problems. However, deep learning for 3D reconstruction is still at its infancy due to its unique challenges and varying pipelines. To stimulate future research, this paper presents a review of recent progress in deep learning methods for Multi-view Stereo (MVS), which is considered as a crucial task of image-based 3D reconstruction. It also presents comparative results on several publicly available datasets, with insightful observations and inspiring future research directions.