Arlo0o/StereoScene
[IJCAI 2024]Official PyTorch Implementation of Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion
StereoScene helps autonomous driving engineers and robotics researchers create accurate 3D semantic maps of environments from vehicle camera footage. It takes in stereo camera images (RGB) and LiDAR point clouds, then outputs a dense 3D representation of the scene, identifying objects and free space. This is crucial for precise navigation and environmental understanding in self-driving cars and robots.
111 stars. No commits in the last 6 months.
Use this if you need to infer a complete, dense 3D semantic understanding of an outdoor environment using stereo camera inputs and optionally LiDAR, even when parts of the scene are initially hidden or ambiguous.
Not ideal if your application doesn't involve outdoor scene understanding, requires real-time processing on embedded systems with limited computational resources, or if you only have monocular camera input.
Stars
111
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 31, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Arlo0o/StereoScene"
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.