Common House

Common House project received Arts Intergrative Interdisicplinary (AiiR) Faculty Grant from Arts Engine.

The project focuses at the problem of floor plan analysis and generation using neural networks.

An example from the annotated data created.

The main obstacle that has emerged in creating more real-life plans is the lack of databases that are tailored for these architecture applications. The Common House project aims at creating a large-scale dataset for plans with semantic information. Precisely, our data creation pipeline consists of annotating different components of a floor plan, for e.g. Dining Room, Kitchen, Bed Room, etc.

How to Contribute?

We are looking for people who can annotate pre-loaded floor plans, or upload their own floor plans and annotate them.

To get a brief idea about the annotation, please have a look at the following video.
If you are students from the Taubman College and interested in contributing, please fill this Google form.
Otherwise, to gain access to an annotation server, please fill this Google form.
To standardize the annotation process, we have made a list of the kinds of rooms that are to be annotated. Please go through this annotation guide to have a closer look at the components that are to be annotated.

Annotation Guide

To assist the annotation, we have made an exhaustive list of components(classes) in a floor plan, for e.g. Bedroom, Kitchen, etc. A detail on these classes can be found here.

Overall, we have following classes: