alyssaq / 3dreconstruction
3D reconstruction, sfm with Python3
Stars: ✭ 213
Programming Languages
Projects that are alternatives of or similar to 3dreconstruction
cv-arxiv-daily
🎓Automatically Update CV Papers Daily using Github Actions (Update Every 12th hours)
Stars: ✭ 216 (+1.41%)
Mutual labels: sfm, 3d-reconstruction
Openmvg
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
Stars: ✭ 3,902 (+1731.92%)
Mutual labels: 3d-reconstruction, sfm
simple-sfm
A readable implementation of structure-from-motion
Stars: ✭ 19 (-91.08%)
Mutual labels: sfm, 3d-reconstruction
slam-python
SLAM - Simultaneous localization and mapping using OpenCV and NumPy.
Stars: ✭ 80 (-62.44%)
Mutual labels: numpy, 3d-reconstruction
Dagsfm
Distributed and Graph-based Structure from Motion
Stars: ✭ 269 (+26.29%)
Mutual labels: 3d-reconstruction, sfm
Opensfm
Open source Structure-from-Motion pipeline
Stars: ✭ 2,342 (+999.53%)
Mutual labels: 3d-reconstruction, sfm
Fashion Recommendation
A clothing retrieval and visual recommendation model for fashion images.
Stars: ✭ 193 (-9.39%)
Mutual labels: numpy
Pixel2meshplusplus
Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation. In ICCV2019.
Stars: ✭ 188 (-11.74%)
Mutual labels: 3d-reconstruction
Rootpy
A pythonic interface for the ROOT libraries on top of the PyROOT bindings.
Stars: ✭ 186 (-12.68%)
Mutual labels: numpy
Xtensor
C++ tensors with broadcasting and lazy computing
Stars: ✭ 2,453 (+1051.64%)
Mutual labels: numpy
Tsalib
Tensor Shape Annotation Library (numpy, tensorflow, pytorch, ...)
Stars: ✭ 209 (-1.88%)
Mutual labels: numpy
Cheatsheets Ai
Essential Cheat Sheets for deep learning and machine learning researchers https://medium.com/@kailashahirwar/essential-cheat-sheets-for-machine-learning-and-deep-learning-researchers-efb6a8ebd2e5
Stars: ✭ 14,095 (+6517.37%)
Mutual labels: numpy
Horizonnet
Pytorch implementation of HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation.
Stars: ✭ 195 (-8.45%)
Mutual labels: 3d-reconstruction
3D reconstruction
3D reconstruction from 2D images pipeline
Steps:
- Detect 2D points
- Match 2D points across 2 images
- Epipolar geometry
3a. If both intrinsic and extrinsic camera parameters are known, reconstruct with projection matrices.
3b. If only the intrinsic parameters are known, normalize coordinates and calculate the essential matrix.
3c. If neither intrinsic nor extrinsic parameters are known, calculate the fundamental matrix. - With fundamental or essential matrix, assume P1 = [I 0] and calulate parameters of camera 2.
- Triangulate knowing that x1 = P1 * X and x2 = P2 * X.
- Bundle adjustment to minimize reprojection errors and refine the 3D coordinates.
Note: Steps and code in this repo is my hobby / learning exercise. Ie, its probably not very efficient. If you wish to use a more production-ready library, check out OpenCV's SFM module. I have a docker environment for it at: https://github.com/alyssaq/reconstruction
Prerequisites
- Python 3.5+
- Install OpenCV: Mac installation steps
- pip install -r requirements.txt
Example 3D cube reconstruction
$ python3 cube_reconstruction.py
Example Dino 3D reconstruction from 2D images
Download images from http://www.robots.ox.ac.uk/~vgg/data/data-mview.html and place into imgs/dinos
$ python3 example.py
Detected points and matched across 2 images.
3D reconstructed dino with essential matrix
3D to 2D Projection
$ python3 camera.py
3D points of model house from Oxford University VGG datasets.
Projected points
Datasets
- Oxford University, Visual Geometry Group: http://www.robots.ox.ac.uk/~vgg/data/data-mview.html
- EPFL computer vision lab: http://cvlabwww.epfl.ch/data/multiview/knownInternalsMVS.html
References
License
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].