zubair-irshad/CenterSnap
Pytorch code for ICRA'22 paper: "Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation"
This project helps roboticists and computer vision engineers precisely identify and understand objects in 3D space. It takes an image from a standard camera (RGB-D) as input and outputs the 3D shape, exact position (6D pose), and size of multiple objects detected within that single image. This is ideal for those developing robotic manipulation systems, augmented reality applications, or inventory management solutions.
325 stars. No commits in the last 6 months.
Use this if you need to quickly and accurately determine the 3D characteristics and spatial location of multiple objects from a single camera view.
Not ideal if your application requires object detection with custom camera parameters without the ability to finetune the network with your own data.
Stars
325
Forks
57
Language
Jupyter Notebook
License
—
Category
Last pushed
Jun 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/zubair-irshad/CenterSnap"
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.