Reconstructing 3D Shapes as a Union of Boxes from Multi-View Images

dc.contributor.advisorGong, Minglun
dc.contributor.authorYang, Zihan
dc.date.accessioned2023-05-02T17:45:12Z
dc.date.available2023-05-02T17:45:12Z
dc.date.copyright2023-05-02
dc.date.created2023-04-21
dc.degree.departmentSchool of Computer Scienceen_US
dc.degree.grantorUniversity of Guelphen
dc.degree.nameMaster of Scienceen_US
dc.degree.programmeComputer Scienceen_US
dc.description.abstractReconstructing object shapes from images has become increasingly important in various fields, such as computer vision, robotics, augmented reality. While approaches for reconstructing shapes with varying levels of detail have been proposed, balancing representation accuracy and model complexity remains a challenge. To address this challenge, we propose an end-to-end approach for reconstructing object shapes from multiple images using a union of box primitives. Our approach offers a simpler and more efficient 3D representation of objects without the need for intermediate products such as voxels, resulting in faster inference times. Additionally, we introduce an auxiliary task to aid in learning how to extract and transform spatial features from images without requiring camera calibrations. Extensive experiments demonstrate that our method can produce comparable results to approaches that require 3D voxelized input while utilizing only 2D images as input. Furthermore, our method significantly outperforms the aforementioned approaches in terms of inference time.en_US
dc.identifier.urihttps://hdl.handle.net/10214/27518
dc.language.isoenen_US
dc.publisherUniversity of Guelphen
dc.rights.licenseAll items in the Atrium are protected by copyright with all rights reserved unless otherwise indicated.
dc.subjectReconstructing object shapesen_US
dc.subjectImagesen_US
dc.subject3D representationen_US
dc.titleReconstructing 3D Shapes as a Union of Boxes from Multi-View Imagesen_US
dc.typeThesisen

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Yang_Zihan_202305_MSc.pdf
Size:
1.61 MB
Format:
Adobe Portable Document Format
Description:
Thesis