Turning 2D floor plans into 3D-ready JSON with Detectron2
Turning 2D floor plans into 3D-ready JSON with Detectron2
Hey HN, For the past few weekends, I have been working on a computer vision pipeline to solve a specific PropTech problem: turning messy, highly occluded 2D floor plans into clean, structured data for 3D extrusion. I originally built this as a demo for a firm. The Stack & Architecture I built an instance segmentation pipeline that relies strictly on pixel-perfect masking to extract the geometry. The Backbone: Swin Transformer + Detectron2 + OpenCV Training: Trained on 1024x1024 images using an RTX 4090. Inference: Runs on CPU in < 10s. Demo Performance: 67.1% AP50 for instance segmentation masks, and 38.2% AP across the strict 0.50:0.95 IoU thresholds. Why I'm posting: A lot of virtual staging and architectural startups have beautiful Three.js rendering engines, but still rely on manual data entry to build the base geometry. I built this specifically as an extraction engine to sit underneath those UIs. If you are in PropTech or building a product that could benefit from embedding this model under the hood, I would love to chat.
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Incorrect prediction on native model
Similar products
Wanaplan - WebGL application to create 2D/3D floor plans
t-SNE in Go, with 2D and 3D MNIST visualizations
2D-to-3D Floorplan Editor
Plotting and 2D/3D UI
Veusz – 2D and 3D interactive scientific plotting
Simulating Galaxies in 2D
8Land is a 2D pixelart metaverse
Cedreo easy Floor Plan Software. Instant 3D floor plans from 2D drawing
2D/3D Geovisualization of Traveling Salesman Problem Heuristics
landscape desing software, 2D and 3D visualization