3dlg-hcvc/plan2scene
Official implementation of the paper Plan2Scene.
Plan2Scene converts 2D floorplans and a set of photos into a fully textured 3D model of a residence. It takes architectural floorplans and interior photographs as input, and outputs a realistic, navigable 3D scene. This tool is ideal for interior designers, architects, real estate agents, or virtual tour creators looking to visualize or present residential spaces.
588 stars. No commits in the last 6 months.
Use this if you need to quickly generate detailed 3D models of homes for virtual tours, design presentations, or digital staging from existing floorplans and photographs.
Not ideal if you only have a floorplan and no interior photos, or if you need to model complex, non-residential buildings with unique architectural features.
Stars
588
Forks
77
Language
Python
License
MIT
Category
Last pushed
Oct 20, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/3dlg-hcvc/plan2scene"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
3DOM-FBK/deep-image-matching
Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM...
suhangpro/mvcnn
Multi-view CNN (MVCNN) for shape recognition
zouchuhang/LayoutNet
Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a...
andyzeng/tsdf-fusion-python
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
andyzeng/tsdf-fusion
Fuse multiple depth frames into a TSDF voxel volume.