Login | Register

3D Point Cloud Reconstruction of a Single Image using Deep Learning


3D Point Cloud Reconstruction of a Single Image using Deep Learning

Zamani, AmirHossein (2023) 3D Point Cloud Reconstruction of a Single Image using Deep Learning. Masters thesis, Concordia University.

[thumbnail of Zamani_MA_F2023.pdf]
Text (application/pdf)
Zamani_MA_F2023.pdf - Accepted Version
Restricted to Repository staff only until 1 September 2025.
Available under License Spectrum Terms of Access.


An essential yet challenging step in the 3D reconstruction problem is to train a machine or a robot to model 3D objects. Many 3D reconstruction applications depend on real-time data processing, so computational efficiency is a fundamental requirement in such systems. Despite considerable progress in 3D reconstruction techniques in recent years, developing efficient algorithms for real-time implementation remains an open problem. The present study addresses current issues in the high-precision reconstruction of objects displayed in a single-view image with sufficiently high accuracy and computational efficiency. To this end, we propose two neural frameworks: a CNN-based autoencoder architecture called Fast-Image2Point (FI2P) and a transformer-based network called Transformer+CNN (TransCNN3D). These frameworks consist of two stages: perception and construction. The perception stage addresses the understanding and extraction process of the underlying contexts and features of the image. The construction stage, on the other hand, is responsible for recovering the 3D geometry of an object by using the knowledge and contexts extracted in the perception stage. More specifically, the FI2P is a simple yet powerful architecture to reconstruct 3D objects from images faster (in real-time) without losing accuracy. Then, the TransCNN3D framework provides a more accurate 3D reconstruction without losing computational efficiency. The point cloud representation is used for the output of the reconstruction frameworks. The ShapeNet dataset is utilized to compare the proposed method with the existing ones in terms of computation time and accuracy. Simulations demonstrate the superior performance of the strategy.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Electrical and Computer Engineering
Item Type:Thesis (Masters)
Authors:Zamani, AmirHossein
Institution:Concordia University
Degree Name:M.A. Sc.
Program:Electrical and Computer Engineering
Date:July 2023
Thesis Supervisor(s):Aghdam, Amir G.
ID Code:992634
Deposited By: AmirHossein Zamani
Deposited On:15 Nov 2023 15:27
Last Modified:15 Nov 2023 15:27
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top