By Chen Liu*, Jiaye Wu*, and Yasutaka Furukawa (* indicates equal contribution)
This paper proposes FloorNet, a novel neural network, to turn RGBD videos of indoor spaces into vector-graphics floorplans. FloorNet consists of three branches, PointNet branch, Floorplan branch, and Image branch. For more details, please refer to our Arxiv paper or visit our project website. This is a follow-up work of our floorplan transformation project which you can find here.
Python 2.7, TensorFlow (>= 1.0), numpy, opencv 3.
We collect 155 scans of residential units and annotated corresponding floorplan information. Among 155 scans, 135 are used for training and 20 are for testing. We convert both training data and testing data to tfrecords files which can be downloaded here. Please put the downloaded files under folder data/.
To train the network from scratch, please run:
python train.py --restore=0To evaluate the performance of our trained model, please run:
python evaluate.pyIf you have any questions, please contact me at chenliu@wustl.edu.