artmortal93/PatchMatchStereo_CUDA
PatchMatch Stereo with Red-Black modifiaction and Row Parallel modification for massively parallel computing
This project helps create detailed 3D models from pairs of stereo images, much like how human eyes perceive depth. It takes two images of the same scene, captured from slightly different angles, and quickly generates a 'depth map' that shows the distance of each point in the scene. This tool is for engineers, researchers, or anyone working in computer vision who needs fast and accurate 3D reconstruction for tasks like robotic navigation or environmental mapping.
No commits in the last 6 months.
Use this if you need to rapidly generate accurate depth maps from stereo image pairs for 3D reconstruction tasks, especially if you have access to a powerful GPU.
Not ideal if you do not have access to a CUDA-enabled GPU or if your workflow involves single images rather than stereo pairs.
Stars
16
Forks
3
Language
C
License
—
Category
Last pushed
Dec 02, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/artmortal93/PatchMatchStereo_CUDA"
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.