- Fișa disciplinei:
- FI-D SFA-138 Tehnologii avansate de captare 3D.pdf
- Department:
- Study of Form and Ambience
- Course Leader:
- conf. Andreea Iosif
- Learning outcomes:
- General Objective:
Acquiring an in-depth understanding of contemporary 3D capture technologies and how they can be applied in the documentation, analysis, and development of interior architecture and product design projects.
Specific Objectives:
▪ Gaining knowledge of and using methods such as photogrammetry, 3D scanning, and AI-based reconstruction
▪ Understanding the types of data resulting from capture processes and managing them within workflows specific to design
▪ Developing the technical and analytical skills necessary to integrate this data into CAD, BIM models, or advanced digital visualizations
▪ Building the capacity to critically select appropriate methods based on the project's purpose and the specific object or space under study
▪ Fostering a reflective and innovative attitude in using new digital technologies within a professional context
- Content:
- Module 1: First Steps in 3D Capture Technologies
Week 1:
Introduction to 3D Data Acquisition
Course overview, objectives, and applicability in product design and interior architecture.
History of 3D capture technologies: from photogrammetry to 3D scanning and recent innovations.
Week 2:
Principles of Photogrammetry
The theory of photogrammetry: image capture process, triangulation, and 3D reconstruction.
Software and tools used in photogrammetry.
Week 3:
3D Data Management and Processing
Types of data (meshes, point clouds, textures) and file format standards.
Workflow for processing captured data (cleaning, optimization, integration).
Week 4:
A Practical Application
Carrying out object photogrammetry in Reality Capture.
Module 2: 3D Scanning
Week 5:
3D Scanning Technologies
Types of 3D scanners (laser, LIDAR, structured light) and their operating principles.
Comparison of the advantages and disadvantages of different methods.
Week 6:
Applicability of 3D Scanning in Design
Case studies and practical examples.
Integrating scan data into digital workflows and design projects.
Week 7:
Integrating 3D Data into CAD and BIM
Using 3D data in computer-aided design (CAD) software and Building Information Modeling (BIM).
Industry case studies and practical examples.
Week 8:
A Practical Application
2D Survey / BIM Model from a Point Cloud.
Module 3: Integration of Artificial Intelligence (AI) and Emerging Technologies
Week 9:
Introduction to NeRF (Neural Radiance Fields)
Presentation of the NeRF concept and how it redefines 3D data capture using AI.
Examples of recent projects and research using NeRF in architecture and product design.
Week 10:
AI-Supported Data Capture Tools and Platforms
Specialized software and platforms that integrate AI for 3D space capture and reconstruction.
Practical usage demonstrations.
Week 11:
A Practical Application
Performing data capture in LumaAI.
Module 4: Project Development
Week 12:
Final Project (p1)
Hands-on sessions for data capture and reconstruction of real-world objects/spaces.
Team collaboration to solve data capture challenges.
Week 13:
Final Project (p2)
Reconstruction of the BIM model from the point cloud.
Conversion of the model into a mesh and texture mapping.
Week 14:
Final Project Presentations
Students present their final projects using the 3D capture technologies discussed throughout the course.
- Teaching Method:
- - Interactive learning sessions, explanations, debates, case studies
- The course utilizes the existing data capture infrastructure of the Mac Popescu Experimental Workshop at UAUIM
- Assessment:
- 30% active participation in lectures and practical work sessions;
70% final project and presentation
Passing threshold: 45%, with mandatory attendance at at least 50% of the scheduled sessions.
- Bibliography:
- 1. James B. Campbell & Randolph H. Wynne – Introduction to Remote Sensing
2. Szeliski, Richard – Computer Vision: Algorithms and Applications
3. Beraldin, J-A. et al. – 3D Imaging for Cultural Heritage (Digital Imaging and Computer Vision)
4. Boehler, W. & Marbs, A. – 3D Scanning and Photogrammetry for Heritage Recording: A Comparison
5. Mildenhall, Ben et al. – NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
6. Rematas, K., Ritschel, T., Fritz, M., & Kim, K. – Neural Rendering Survey