zouchuhang/LayoutNet
Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image"
This tool helps architects, interior designers, or real estate professionals quickly understand the 3D layout of a room from a single 2D image. You input a standard panoramic or perspective photo, and it outputs a detailed 3D reconstruction of the room's shape, including wall boundaries and corner locations.
431 stars. No commits in the last 6 months.
Use this if you need to rapidly generate a 3D model of a room's structure from a single image for planning, visualization, or analysis, particularly for standard 'Manhattan' (cuboid) layouts.
Not ideal if you need to reconstruct highly complex, non-standard, or extremely irregular room shapes that deviate significantly from cuboid structures.
Stars
431
Forks
94
Language
MATLAB
License
MIT
Category
Last pushed
Jan 19, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/zouchuhang/LayoutNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
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
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.
google/stereo-magnification
Code accompanying the SIGGRAPH 2018 paper "Stereo Magnification: Learning View Synthesis using...