KEYWORD |
Can You Furnish It? Generative Furniture Arrangement in 3D House Floorplans
keywords 3D MODELS, ARTIFICIAL INTELLIGENCE, DEEP LEARNING, COMPUTER V, GENERATIVE AI
Reference persons TATIANA TOMMASI
External reference persons Antonio Alliegro, Francesca Pistilli
Research Groups DAUIN - GR-23 - VANDAL - Visual and Multimodal Applied Learning Lab
Thesis type RESEARCH / EXPERIMENTAL
Description The research project endeavors to push the boundaries of generative models in the domain of furniture arrangement within houses. While existing studies concentrate on 3D scene generation or furniture placement within individual rooms, this thesis seeks to pioneer a more expansive and adaptable approach. The primary objective is to design a model that intelligently positions 3D mesh models throughout an entire house. It encompasses the intricate tasks of selecting appropriate objects from a diverse collection of 3D objects for each room and arranging them spatially within the provided space constraints.
See also thesis-3d-furniture.pdf
Required skills - Excellent programming skills (Python and PyTorch) are required
- Candidates must have strong motivation
- Previous knowledge of the 3D understanding is not required, although it is preferred
Deadline 15/05/2024
PROPONI LA TUA CANDIDATURA