IceTTTb/PlaneTR3D
[ICCV'21] PlaneTR: Structure-Guided Transformers for 3D Plane Recovery
This project helps computer vision researchers and robotics engineers convert complex 2D image data into structured 3D plane representations. It takes in depth images and detected line segments, then outputs an understanding of the dominant planar surfaces in a scene. This is useful for anyone building systems that need to perceive and interact with real-world environments.
101 stars. No commits in the last 6 months.
Use this if you need to extract precise 3D planar information from depth images to build or analyze 3D models of indoor environments.
Not ideal if you're looking for a general-purpose 3D object detection tool or if your primary input is LiDAR data rather than depth images.
Stars
101
Forks
12
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 09, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/IceTTTb/PlaneTR3D"
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.