Intelligent Interior Design - Style Compatibility of 3D Furniture Models using Neural Networks

• Thesis title in Czech: Inteligentní návrh interiérů - Kompatibilita stylu 3D modelů nábytku pomocí neuronových sítí
• Thesis title in English: Intelligent Interior Design - Style Compatibility of 3D Furniture Models using Neural Networks
• Key words: 3D grafika; neuronové sítě
• English key words: 3D graphics; neural networks; metric learning; style similarity
• Academic year of topic announcement: 2018/2019
• Thesis type: diploma thesis
• Thesis language: angličtina
• Department: Department of Software and Computer Science Education (32-KSVI)
• Supervisor: Mgr. Martin Mirbauer
• Author: hidden - assigned and confirmed by the Study Dept.
• Date of registration: 19.07.2019
• Date of assignment: 19.07.2019
• Confirmed by Study dept. on: 25.07.2019
• Date and time of defence: 03.02.2020 09:00
• Date of electronic submission: 06.01.2020
• Date of submission of printed version: 06.01.2020
• Date of proceeded defence: 03.02.2020
• Opponents: Mgr. Jakub Střelský

Guidelines

The goal of this diploma thesis project is to measure the style compatibility between 3D furniture models from different categories, then find the most compatible objects for a given piece of furniture. For example, given a Scandinavian style table, find a chair and a lamp that match the table. This makes it possible for users, e.g graphic designers without knowledge of interior design, to create scenes by arranging suggested furniture.
While a variety of deep neural networks that can classify 3D objects into different categories have been developed, neural networks that compare styles between objects from different categories is still a new direction.

References

[1] C. R. Qi, H. Su, K. Mo, and L. J. Guibas. Pointnet: Deep learning on point sets for 3d classification and segmentation. arXiv preprint arXiv:1612.00593, 2016.
[2] I. Lim, A. Gehre, L. Kobbelt, Identifying style of 3d shapes using deep metric learning, in: Computer Graphics Forum, Vol. 35, Wiley Online Library, 2016, pp. 207–215.
[3] J. Wang, Y. Song, T. Leung, C. Rosenberg, J. Wang, J. Philbin, B. Chen, and Y. Wu. "Learning Fine-grained Image Similarity with Deep Ranking." In CVPR,
[4] Tianqiang Liu, Aaron Hertzmann, Wilmot Li, and Thomas Funkhouser. 2015. Style Compatibility for 3D Furniture Models. ACM Trans. on Graphics (Proc. of SIGGRAPH) 34, 4 (2015), 85:1–9.
[5] Zhaoliang Lun, Evangelos Kalogerakis, and Alla Sheffer, Elements of style: Learning perceptual shape style similarity, ACM Transactions on Graphics (TOG), vol. 34, no. 4, pp. 84, 2015.