Abstract
Abstract. Objects and structures realized by connecting and bending wires are common in modern architecture, furniture design, metal sculpting, etc. The 3D reconstruction of such objects with traditional range- or image-based methods is very difficult and poses challenges due to their unique characteristics such as repeated structures, slim elements, holes, lack of features, self-occlusions, etc. Complete 3D models of such complex structures are normally reconstructed with lots of manual intervention as automated processes fail in providing detailed and accurate 3D reconstruction results.This paper presents the image-based 3D reconstruction of the Shukhov hyperboloid tower in Moscow, a wire structure built in 1922, composed of a series of hyperboloid sections stacked one to another to approximate an overall conical shape. A deep learning approach for image segmentation was developed in order to robustly detect wire structures in images and provide the basis for accurate corresponding problem solutions. The developed WireNet convolution neural network (CNN) model has been used to aid the multi-view stereo (MVS) process and to improve robustness and accuracy of the image-based 3D reconstruction approach, otherwise not feasible without masking the images automatically.
Highlights
Wire structures, such as radio poles, spider webs, wire jewelry, etc., pose challenges for active and passive 3D reconstruction techniques
Complicated interweaved wire structures usually have a large number of holes, repeated patters, textureless surfaces, specular reflections, ambiguities and thin elements that could be too small to be detected by laser scanners or accurately matched by multi-view stereo (MVS) algorithms
Such complex structures are normally reconstructed with lots of manual intervention as automated processes fail in providing detailed and accurate 3D reconstruction results
Summary
Wire structures, such as radio poles, spider webs, wire jewelry, etc., pose challenges for active and passive 3D reconstruction techniques. Complicated interweaved wire structures usually have a large number of holes, repeated patters, textureless surfaces, specular reflections, ambiguities and thin elements that could be too small to be detected by laser scanners or accurately matched by multi-view stereo (MVS) algorithms. Such complex structures are normally reconstructed with lots of manual intervention as automated processes fail in providing detailed and accurate 3D reconstruction results. Inspired by the progress of deep learning techniques in solving challenging tasks in photogrammetry and computer vision, this work tries to exploit a “human-like” machine learning approach to perform object masking in images and improve the MVS process. Image masking is a very time-consuming part of the image processing 3D pipeline and often the only way to achieve detailed 3D results
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
