suryanshkumar/online-joint-depthfusion-and-semantic
A Real-Time Online Learning Framework for Joint 3D Reconstruction and Semantic Segmentation for Indoor Scene.
This project helps robotics engineers and 3D mapping specialists create detailed digital models of indoor spaces in real-time. By taking noisy depth sensor data, camera movement information, and 2D labels (like 'wall' or 'chair'), it produces a cleaned-up 3D reconstruction of the scene along with semantic labels for different objects and surfaces. This is ideal for applications needing to understand both the shape and meaning of objects within an indoor environment.
No commits in the last 6 months.
Use this if you need to perform real-time 3D reconstruction and identify objects in indoor scenes using depth sensor data for robotics, augmented reality, or surveying applications.
Not ideal if your primary need is for outdoor scene mapping, processing only 2D images, or if you don't require semantic labeling alongside your 3D models.
Stars
67
Forks
7
Language
Python
License
—
Category
Last pushed
Mar 19, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/suryanshkumar/online-joint-depthfusion-and-semantic"
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.