GenScan: A Generative Method for Populating Parametric 3D Scan Datasets
This system facilitates data augmentation for researchers and practitioners in 3D computer vision, generative design, and 3D deep learning, where the availability of rich 3D geometry datasets is a significant bottleneck.
This paper introduces GenScan, a generative system that addresses the scarcity of complex 3D datasets by creating parametric variations of existing 3D scans. It takes a captured 3D scan and outputs alternative building layouts, including walls, doors, furniture, and textures.
The availability of rich 3D datasets corresponding to the geometrical complexity of the built environments is considered an ongoing challenge for 3D deep learning methodologies. To address this challenge, we introduce GenScan, a generative system that populates synthetic 3D scan datasets in a parametric fashion. The system takes an existing captured 3D scan as an input and outputs alternative variations of the building layout including walls, doors, and furniture with corresponding textures. GenScan is a fully automated system that can also be manually controlled by a user through an assigned user interface. Our proposed system utilizes a combination of a hybrid deep neural network and a parametrizer module to extract and transform elements of a given 3D scan. GenScan takes advantage of style transfer techniques to generate new textures for the generated scenes. We believe our system would facilitate data augmentation to expand the currently limited 3D geometry datasets commonly used in 3D computer vision, generative design, and general 3D deep learning tasks.