Architectural Drawings Recognition and Generation through Machine Learning (2018)

Notes on a 2018 paper by Weixin Huang and Hao Zheng

A generative adversarial network to superimpose coloured rectangles on architectural floor plans based on room type (Bedroom, kitchen, etc.). Worked really well for some rooms - it even picked up a few mistakes in the human labelling.

Read the paper: ACADIA, ResearchGate, PDF.

machine-learning bim cad construction

Pix2PixHD used to generate zoning maps of floor plans
Detail improves with number of epochs - ResNet used to prevent overfitting
CGAN - Conditional Generative Adversarial Networks - punish trining going in wrong direction
Pix2PixHD - 5 groups of convolutional layers, 9 groups of residual network layers, 5 groups of deconvolutional layers
Using PyTorch - images from lianjia.com
Labels used: Walkway, Bedroom, Living Room, Kitchen, Toilet, Dining Room, Balcony, Window, Door
115 image pairs - 100 training, 15 testing ~ 2hrs to train one network
Works well in recognising bedroom, kitchen, toilet & balcony - normally well-defined by walls and specific furniture
Less successful for walkway/living room - but some architects got this wrong when labelling test data (done by Architectural students)
Struggled with non-orthogonal shapes
In one image, GAN found mis-labelled data. Later found 4 errors in human-labelled data, which didn't lead to training in the wrong direction - pretty robust network.
Generating plans from zones - sometimes put furniture facing the wrong way. Some architects agreed with the network's furniture position above the position in the test images.
2-pixel convolutions. Residual network avoids overfitting.
Trained to 80 epochs - loss value stabilised after that
The paper looks at individual neurons' feature detection
Bedrooms/balconies often activated together