GenScan: A Generative Method for Populating Parametric 3D Scan Datasets

Abstract

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.

Mutual Scene Synthesis for Mixed Reality Telepresence

“…GSACNet combines graph attention, siamese, and autoenoder networks to perform iterative scene synthesis for new or constrained scenes. For the training process, in order to achieve robust results with limited scene priors, we propose utilizing the parametric data augmentation method introduced in [21]. In this method, after building parametric floorplans of the rooms, boundary geometry and their adjacent furniture are constantly permutated while maintaining a set of functional constraints within the room.…”

Contextual Scene Augmentation and Synthesis via GSACNet

“…In parametric design, various design elements in a procedural model can be transformed using input parameters while maintaining their topological relationships with each other. Work of [16,17,19] are examples of systems that utilize parametric workflows for generating various space layout configurations.…”

“…We use a modified version of the scene augmentation method introduced in [16]. Furthermore, we run two sets of area checks: (a) to check whether the area of the open space of the room is not larger than a certain percentage of the overall area of the room.…”

“…Below we provide additional details of the modified version of the scene augmentation method introduced in [16], and our data filtering techniques for the parametric data augmentation. We calculate the center coordinates of each bounding box assigned to objects and perform a closest point search with a parametric wall system to find the closest wall.…”

GenFloor: Interactive Generative Space Layout System via Encoded Tree Graphs

“…Chaillou expands this approach by nesting three models (footprint, program, and furnishing) to generate floorplans, given a set of initial conditions and constraints. Extracting and manipulating existing layouts from images and sketches using model retrieval methods [36,6] has also been used as a data augmentation method for generating new layouts [34].…”