dgrzech / Sobfu
Licence: bsd-3-clause
real-time 3D reconstruction of non-rigidly deforming scenes using depth data
Stars: ✭ 113
Projects that are alternatives of or similar to Sobfu
Dynamicfusion
Implementation of Newcombe et al. CVPR 2015 DynamicFusion paper
Stars: ✭ 267 (+136.28%)
Mutual labels: 3d-reconstruction, opencv
Opensfm
Open source Structure-from-Motion pipeline
Stars: ✭ 2,342 (+1972.57%)
Mutual labels: 3d-reconstruction, opencv
Sltk
An OpenCV-based structured light processing toolkit.
Stars: ✭ 151 (+33.63%)
Mutual labels: 3d-reconstruction, opencv
3dv tutorial
An Invitation to 3D Vision: A Tutorial for Everyone
Stars: ✭ 571 (+405.31%)
Mutual labels: 3d-reconstruction, opencv
Opencv Electron
Example for using opencv4nodejs with electron.
Stars: ✭ 107 (-5.31%)
Mutual labels: opencv
Arkit Multiplayer
ARKit multiplayer experience explanation & example
Stars: ✭ 106 (-6.19%)
Mutual labels: opencv
Imagefeaturedetector
A C++ Qt GUI desktop program to calculate Harris, FAST, SIFT and SURF image features with OpenCV
Stars: ✭ 112 (-0.88%)
Mutual labels: opencv
Aruco Markers
Working examples/tutorial for detection and pose estimation of ArUco markers with C++
Stars: ✭ 112 (-0.88%)
Mutual labels: opencv
Unsupervised Depth Completion Visual Inertial Odometry
Tensorflow implementation of Unsupervised Depth Completion from Visual Inertial Odometry (in RA-L January 2020 & ICRA 2020)
Stars: ✭ 109 (-3.54%)
Mutual labels: 3d-reconstruction
Selfdrivingcar
A collection of all projects pertaining to different layers in the SDC software stack
Stars: ✭ 107 (-5.31%)
Mutual labels: opencv
Ios Rubik Solver
An iOS app that detects a 3x3 Rubik's cube, recognizes the color of all cubies, solves it and provides a 3D visualisation of the solving process.
Stars: ✭ 111 (-1.77%)
Mutual labels: opencv
Hiitpi
A workout trainer Dash/Flask app that helps track your HIIT workouts by analyzing real-time video streaming from your sweet Pi using machine learning and Edge TPU..
Stars: ✭ 106 (-6.19%)
Mutual labels: opencv
Studybook
Study E-Book(ComputerVision DeepLearning MachineLearning Math NLP Python ReinforcementLearning)
Stars: ✭ 1,457 (+1189.38%)
Mutual labels: opencv
Awesome Face Detection
Compare with various detectors - s3fd, dlib, ocv, ocv-dnn, mtcnn-pytorch, face_recognition
Stars: ✭ 106 (-6.19%)
Mutual labels: opencv
Opencvjs
Complete opencvjs (With the lastest OpenCV 4.0.0+)
Stars: ✭ 108 (-4.42%)
Mutual labels: opencv
Sgnn
[CVPR'20] SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
Stars: ✭ 112 (-0.88%)
Mutual labels: 3d-reconstruction
Opencv Ndarray Conversion
NumPy ndarray ⇋ OpenCV Mat conversion, that just works.
Stars: ✭ 107 (-5.31%)
Mutual labels: opencv
Jpdaf tracking
A tracker based on joint probabilistic data association filtering.
Stars: ✭ 107 (-5.31%)
Mutual labels: opencv
sobfu
software for 3d reconstruction of non-rigidly deforming scenes using depth data, based on sobolevfusion
dependencies
- boost
- nvidia gpu with cuda >8.0
- opencv
- pcl 1.8.1
- vtk
installation
to install, run source setup.sh -a
usage
./build/bin/app /path/to/data /path/to/params <--enable-viz> <--enable-log> <--verbose>
- the data directory must include folders
color
anddepth
- the folder
params
has files with recommended parameters for some of the scenes from volumedeform and killingfusion datasets
options
- with
--enable-viz
, screenshots from the pcl viewer will be logged in .png format to/path/to/data/screenshots
- with
--enable-log
, meshes computed from the model tsdf's via marching cubes will be logged in .vtk format to/path/to/data/meshes
-
--verbose
and--vverbose
control verbosity of the solver
example reconstructions
reconstructions of some of the scenes from the volumedeform and killingfusion projects can be viewed on our youtube playlist
there is a large trade-off between frame rate and reconstruction quality--sample reconstructions ran at approx. 2fps
issues
- drift in longer scenes due to less than perfect registration
- topological changes
references
@InProceedings{Slavcheva_2018_CVPR,
author = {Slavcheva, Miroslava and Baust, Maximilian and Ilic, Slobodan},
title = {SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-Rigid Motion},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}
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].