Comparative Analysis of 3D Human Model Generation - Using 3D Structured Light Scanning and Machine Learning Generation

Aug 3, 2026

Integration of 3D model production from a single 2D RGB picture using machine learning into mainstream human 3D modelling requires significant evaluation data with an appropriate reference value relative to structured light approach scanning. This work bridges the gap between structured light technique and machine learning generation through comparative analysis using qualitative criteria such as accuracy and efficiency. Research is conducted in two phases: controlled data collection with multiple scanning techniques, followed by analysis to establish functional equivalency. Results highlight PIFuHD practicality versus Artec EVA for efficiency and comparable precision, while noting remaining accuracy gaps.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages29

Reading Time1 h 13 min

AccessFree to download

Chapter 1 Introduction

1.1 Objective

1.2 Scope and Limitations

1.3 Organization of the Thesis

Chapter 2 Related Work

2.1 Human 3D Modelling

2.2 3D Scanning using Structured Light Method (STL)

2.3 Machine Learning Scanning Technology

2.4 Comparative Analysis Approach

Chapter 3 Methodology

3.1 General Research Design

3.2 Experimental Setup

3.3 Comparative Analysis Setup

|
FACULTY OF SCIENCE AND TECHNOLOGY
MASTER’S THESIS | | | --- | --- | | Study programme / specialisation:
Engineering Structures and MaterialsMechanical Systems | Spring Semester, 2023
Open / Confidential | | Author:
Md Jubaer Islam Khan | | | Supervisor at UiS: Knut Erik Teigen Giljarhus
Co-supervisor:
External supervisor(s): | | | Thesis title: Comparative Analysis of 3D Human model generation using 3D Structured Light Scanning and Machine Learning generation | | | Credits (ECTS): 30 | | | Keywords:
Comparative Analysis, 3D scanning, 3D modelling , Structured Light Method, Machine Learning generation, Artec EVA, LVD, PIFuHD | Pages: 29
Stavanger, July 27, 2023 | Abstract Integration of 3D model production from a single 2D RGB picture using machine learning into mainstream human 3D modelling requires significant evaluation data with an appropriate reference value relative to structured light approach scanning. The purpose of this work is to bridge the gap between the structured light technique and the machine learning algorithm generation method through a comparative analysis based on qualitative criteria such as accuracy and efficiency. The subsequent research was undertaken in two parts. Phase 1 centered on the experimental setup of the data collecting approach utilizing several scanning techniques on the sample model in a controlled setting, whereas phase 2 focuses on the analysis of the subsequent data to determine functional equivalency. The most significant finding of the comparison study is the practicality of the PIFuHD machine learning algorithm with respect to the Artec EVA scanner in terms of efficiency and equivalent precision. Despite the advancements in Machine learning algorithm for generative 3D modeling, major improvements are necessary to achieve functional parity with the structured light scanning approach in terms of accuracy. ACKNOWLEDGEMENT This thesis is the culmination of my graduate studies in mechanical engineering at the University of Stavanger, Faculty of Natural Sciences and Technology, Norway. I would like to convey my sincerest gratitude to my supervisor, Knut Erik Teigen Giljarhus, who has been an excellent mentor and supporter during my thesis. Without his encouragement, assistance, guidance, and patience, I would not have been able to accomplish my study. Huge gratitude to him for always being on my side and giving me hope. Thank you to the faculty of science and technology at UiS for allowing me to be a part of this incredible master's program, which has helped me widen and strengthen my knowledge, drive, and belief in becoming a world-class mechanical engineer. To my wonderful family and friends, whose support has always inspired me: Table of Contents Chapter 1 Introduction............................................................................................................................ 8 1.1 Objective ....................................................................................................................................... 8 1.2 Scope and Limitations: .................................................................................................................. 9 1.3 Organization of the Thesis: ........................................................................................................... 9 Chapter 2 Related Work ........................................................................................................................ 10 2.1 Human 3D Modelling .................................................................................................................. 10 2.1.1 Human 3D modelling for Sports Engineering....................................................................... 11 2.2 3D Scanning using Structured Light Method (STL) ...................................................................... 11 2.2.1 Artec EVA 3D Scanner ...............................................

FAQs

What is the main goal of the thesis?

To bridge structured light scanning and machine-learning based 3D human model generation by performing a comparative analysis focused on qualitative criteria like accuracy and efficiency.

How is the research conducted?

The study is carried out in two phases: controlled data collection using several scanning techniques on a sample model, and subsequent data analysis to determine functional equivalency.

Which approach performs best in the comparison, and in what aspects?

The PIFuHD machine learning algorithm shows practicality relative to the Artec EVA scanner, especially regarding efficiency and equivalent precision, though functional parity in accuracy still needs improvement.

Aug 3, 2026

Upload by Lucas Martin