This course will be held in English only

3D Modeling and Shape Analysis

In this seminar, we will cover topics from Shape Modelling (i.e. 3D shape creation and design by a user) and Shape Analysis (i.e. the extraction of more abstract information from a collection of 3D shapes). Since Shape Analysis requires there to be a set of 3D shapes for pattern extraction and intuitive Shape Modelling operations often require data-driven feedback, these two topics have a synergistic relationship. For Shape Modelling, we will discuss new interaction concepts and techniques that allow modeling objects and shapes in more intuitive and meaningful ways. In the context of Shape Analysis, we will cover a range of possible shape representations (with their individual benefits and disadvantages) for expressive machine learning techniques such as neural networks.

Contact

Class Information

LabThursdays 10:30 – 12:00

SpracheEnglisch

Credits5 ECTS for B.Sc.
4 ECTS for M.Sc.

Dates

Kick-Off Meeting:
Presentations:

14.10.21
18.11.; 25.11.; 2.12.; 9.12.; 16.12.

Resources

Fields Of Study

Informatik (B.Sc.)
Informatik (M.Sc.)
Media Informatics (M.Sc.)
Software Systems Engineering (M.Sc.)
Data Science (M.Sc.)
Technical Communication (B.Sc.)
Technical Communication (M.Sc.)

Grading

The grade will be calculated as follows:

Written Paper: 50%
Presentation: 50%

Attendance Policy

To pass the course, you need to attend all presentations.

Submission Milestones

All submissions have to be sent to the supervisor until 12:00 (noon) via mail. Include the tag [PDUI] and the name of the topic and the milestone (e.g., “[Seminar] Explainable AI, Report Outline”).

Literature Review & Outline

Prepare 7+ topic-related research papers with a 30-word contribution and benefits statement stating the contribution type. Provide a clear structure for the final paper submission. What is the storyline you want to convey? How are you introducing the topic? What are the arguments you are providing? How are you connecting the papers to each other and your arguments? Include your papers into this structure.

Camera-Ready Presentation Slides

The complete version of your presentation slides (Powerpoint, Keynote, Prezi, ….). Hand in slides which you would confidently use for a presentation on the next day.

Presentation

You present in front of your fellow students and your supervisor. We expect a well-prepared presentation. Test your talk at least once in the room where you are going to present to familiarise yourself with the equipment, and test your slides on the projector in the room. Presentation time will be 20 minutes, followed by a 10-minute discussion where you will receive feedback and questions from your supervisor and your peers. We encourage a constructive feedback interaction where you can learn from each other and have a friendly conversation on how to improve your presentation style.

First Paper Submission

Your paper submission should contain 10 content pages in the ACM CHI template [1]. We expect you to submit a final version without spelling mistakes, with a clear flow of argumentation, a complete bibliography, and including all figures.

[1] https://www.overleaf.com/latex/templates/acm-conference-proceedings-primary-article-template/wbvnghjbzwpc

Paper Feedback

After your presentation, we will meet to give you feedback on your paper submission.

Final Paper Submission

Your paper rebuttal submission should contain 10 content pages in the provided template. We expect you to submit a final version without spelling mistakes, with a clear flow of argumentation, a complete bibliography, and including all figures.

Milestone Dates

Group	Literature Review & Outline (*)	Camera-Ready Presentation Slides (*)	Presentation	First Paper Submission	Paper Feedback (*)	Final Submission
#1	28.10.21	11.11.21	18.11.21	2.12.21	16.12.21	13.01.22
#2	28.10.21	11.11.21	18.11.21	2.12.21	16.12.21	13.01.22
#3	4.11.21	18.11.21	25.11.21	9.12.21	6.1.22	20.01.22
#4	4.11.21	18.11.21	25.11.21	9.12.21	6.1.22	20.01.22
#5	11.11.21	25.11.21	02.12.21	16.12.21	13.01.22	27.01.22
#6	11.11.21	25.11.21	02.12.21	16.12.21	13.01.22	27.01.22
#7	18.11.21	2.12.21	9.12.21	13.01.22	20.01.22	3.02.22
#8	18.11.21	2.12.21	9.12.21	13.01.22	20.01.22	3.02.22
#9	25.11.21	9.12.21	16.12.21	20.01.22	27.01.22	10.02.22
#10	25.11.21	9.12.21	16.12.21	20.01.22	27.01.22	10.02.22

Topics

#1 Combining 2D and 3D Modeling

Patrick Reipschläger and Raimund Dachselt. 2019. DesignAR: Immersive 3D-Modeling Combining Augmented Reality with Interactive Displays. In Proceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces (ISS ’19). Association for Computing Machinery, New York, NY, USA, 29–41. DOI:https://doi.org/10.1145/3343055.3359718

Rahul Arora, Rubaiat Habib Kazi, Tovi Grossman, George Fitzmaurice, and Karan Singh. 2018. SymbiosisSketch: Combining 2D & 3D Sketching for Designing Detailed 3D Objects in Situ. Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, New York, NY, USA, Paper 185, 1–15. DOI:https://doi.org/10.1145/3173574.3173759

#2 Image Based Learning Approaches

Su, Hang, Subhransu Maji, Evangelos Kalogerakis, and Erik Learned-Miller. “Multi-view convolutional neural networks for 3d shape recognition.” In Proceedings of the IEEE international conference on computer vision, pp. 945-953. 2015.

Maron, Haggai, Meirav Galun, Noam Aigerman, Miri Trope, Nadav Dym, Ersin Yumer, Vladimir G. Kim, and Yaron Lipman. “Convolutional neural networks on surfaces via seamless toric covers.” ACM Trans. Graph. 36, no. 4 (2017): 71-1.

#3 Curve and Surface Sketching

Emilie Yu, Rahul Arora, Tibor Stanko, J. Andreas Bærentzen, Karan Singh, and Adrien Bousseau. 2021. CASSIE: Curve and Surface Sketching in Immersive Environments. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (CHI ’21). Association for Computing Machinery, New York, NY, USA, Article 190, 1–14. DOI:https://doi.org/10.1145/3411764.3445158

Fatemeh Abbasinejad, Pushkar Joshi, and Nina Amenta. 2011. Surface patches from unorganized space curves. Computer Graphics Forum 30, 5 (2011), 1379–1387. https://doi.org/10.1111/j.1467-8659.2011.02012.x

#4 Voxel Based Learning Approaches

Maturana, Daniel, and Sebastian Scherer. “Voxnet: A 3d convolutional neural network for real-time object recognition.” In 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 922-928. IEEE, 2015.

Wang, Peng-Shuai, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, and Xin Tong. “O-cnn: Octree-based convolutional neural networks for 3d shape analysis.” ACM Transactions On Graphics (TOG) 36, no. 4 (2017): 1-11.

#5 Gamification for 3D Modeling

Ben Lafreniere and Tovi Grossman. 2018. Blocks-to-CAD: A Cross-Application Bridge from Minecraft to 3D Modeling. In Proceedings of the 31st Annual ACM Symposium on User Interface Software and Technology (UIST ’18). Association for Computing Machinery, New York, NY, USA, 637–648. DOI:https://doi.org/10.1145/3242587.3242602

Wei Li, Tovi Grossman, and George Fitzmaurice. 2012. GamiCAD: a gamified tutorial system for first time autocad users. In Proceedings of the 25th annual ACM symposium on User interface software and technology (UIST ’12). Association for Computing Machinery, New York, NY, USA, 103–112. DOI:https://doi.org/10.1145/2380116.2380131

#6 Point Based Learning Approaches

Qi, Charles R., Hao Su, Kaichun Mo, and Leonidas J. Guibas. “Pointnet: Deep learning on point sets for 3d classification and segmentation.” In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 652-660. 2017.

Thomas, Hugues, Charles R. Qi, Jean-Emmanuel Deschaud, Beatriz Marcotegui, François Goulette, and Leonidas J. Guibas. “Kpconv: Flexible and deformable convolution for point clouds.” In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6411-6420. 2019.

#7 Freehand Modeling

Jackson, Bret, and Daniel F. Keefe. “Lift-off: Using reference imagery and freehand sketching to create 3d models in vr.” IEEE transactions on visualization and computer graphics 22, no. 4 (2016): 1442-1451. DOI: https://dl.acm.org/doi/10.1145/3385956.3418953

Machuca, Mayra D. Barrera, Paul Asente, Wolfgang Stuerzlinger, Jingwan Lu, and Byungmoon Kim. “Multiplanes: Assisted freehand vr sketching.” In Proceedings of the Symposium on Spatial User Interaction, pp. 36-47. 2018. DOI: https://dl.acm.org/doi/10.1145/3325480.3325489

#8 Graph Based Learning Approaches

Wang, Yue, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, and Justin M. Solomon. “Dynamic graph cnn for learning on point clouds.” Acm Transactions On Graphics (tog) 38, no. 5 (2019): 1-12.

Wang, Chu, Babak Samari, and Kaleem Siddiqi. “Local spectral graph convolution for point set feature learning.” In Proceedings of the European conference on computer vision (ECCV), pp. 52-66. 2018.

#9 Interacting with 3D Objects in Mobile AR Environments

Eg Su Goh, Mohd Shahrizal Sunar, and Ajune Wanis Ismail. 2019. 3D Object Manipulation Techniques in Handheld Mobile Augmented Reality Interface: A Review. IEEE Access 7 (2019), 40581–40601. DOI: https://ieeexplore.ieee.org/document/8672062

Philipp Wacker, Oliver Nowak, Simon Voelker and Jan Borchers. ARPen: Mid-Air Object Manipulation Techniques for a Bimanual AR System with Pen & Smartphone. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, CHI ’19, pages 619:1–619:10, ACM, New York, NY, USA, May 2019. DOI: https://doi.org/10.1145/3290605.3300849

#10 Manifold Based Learning Approaches

Masci, Jonathan, Davide Boscaini, Michael Bronstein, and Pierre Vandergheynst. “Geodesic convolutional neural networks on riemannian manifolds.” In Proceedings of the IEEE international conference on computer vision workshops, pp. 37-45. 2015.

Monti, Federico, Davide Boscaini, Jonathan Masci, Emanuele Rodola, Jan Svoboda, and Michael M. Bronstein. “Geometric deep learning on graphs and manifolds using mixture model cnns.” In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5115-5124. 2017.