Journal
DISPLAYS
Volume 70, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.displa.2021.102102
Keywords
Multi-view Stereo; 3D Reconstruction; Plane Sweep; Volumetric Representation; Deep Learning
Ask authors/readers for more resources
This paper provides a comprehensive review on recent deep learning methods for multi-view stereo, categorizing them into depth map based and volumetric based methods. It reviews representative methods in detail and summarizes widely used datasets and metrics for evaluation, while also presenting insightful observations and challenges for future research directions.
Multi-view stereo infers the 3D geometry from a set of images captured from several known positions and viewpoints. It is one of the most important components of 3D reconstruction. Recently, deep learning has been increasingly used to solve several 3D vision problems due to the predominating performance, including the multi-view stereo problem. This paper presents a comprehensive review, covering recent deep learning methods for multi-view stereo. These methods are mainly categorized into depth map based and volumetric based methods according to the 3D representation form, and representative methods are reviewed in detail. Specifically, the plane sweep based methods leveraging depth maps are presented following the stage of approaches, i. e. feature extraction, cost volume construction, cost volume regularization, depth map regression and postprocessing. This review also summarizes several widely used datasets and their corresponding metrics for evaluation. Finally, several insightful observations and challenges are put forward enlightening future research directions.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available