chengzhag/DeepPanoContext
🕸️ [ICCV'21 Oral] Official PyTorch code of DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization
This project helps interior designers, architects, and virtual reality developers understand and recreate realistic 3D indoor scenes from panoramic images. It takes a single 360-degree panoramic photo as input and outputs a detailed 3D reconstruction, including room layout, object detection, and the spatial relationships between objects. This allows users to accurately model existing spaces or design new ones in a virtual environment.
102 stars. No commits in the last 6 months.
Use this if you need to generate a precise 3D model of an indoor space from a single panoramic image for tasks like virtual staging, architectural visualization, or robotics simulation.
Not ideal if you only need a basic 2D floor plan or object recognition, as its strength lies in comprehensive 3D scene understanding.
Stars
102
Forks
12
Language
Python
License
MIT
Category
Last pushed
Aug 17, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/chengzhag/DeepPanoContext"
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.