Project Name | Stars | Downloads | Repos Using This | Packages Using This | Most Recent Commit | Total Releases | Latest Release | Open Issues | License | Language |
---|---|---|---|---|---|---|---|---|---|---|
Instant Ngp | 13,930 | 8 hours ago | 409 | other | Cuda | |||||
Instant neural graphics primitives: lightning fast NeRF and more | ||||||||||
Meshroom | 9,781 | a day ago | 422 | other | Python | |||||
3D Reconstruction Software | ||||||||||
Nerfstudio | 6,578 | 10 hours ago | 394 | apache-2.0 | Python | |||||
A collaboration friendly studio for NeRFs | ||||||||||
Openmvg | 5,074 | a day ago | 226 | mpl-2.0 | C++ | |||||
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion. | ||||||||||
Neuralangelo | 3,429 | 10 days ago | 28 | other | Python | |||||
Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023) | ||||||||||
Awesome_3dreconstruction_list | 3,038 | 2 years ago | 5 | |||||||
A curated list of papers & resources linked to 3D reconstruction from images. | ||||||||||
Alicevision | 2,629 | a day ago | 64 | other | C++ | |||||
Photogrammetric Computer Vision Framework | ||||||||||
Objectron | 1,958 | a year ago | 21 | other | Jupyter Notebook | |||||
Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes | ||||||||||
Scannet | 1,499 | a month ago | 104 | other | C | |||||
Icon | 1,391 | 3 months ago | 28 | other | Python | |||||
[CVPR'22] ICON: Implicit Clothed humans Obtained from Normals |
Meshroom is a free, open-source 3D Reconstruction Software based on the AliceVision Photogrammetric Computer Vision framework.
Learn more details about the pipeline on AliceVision website.
See results of the pipeline on sketchfab.
Continuous integration:
Photogrammetry is the science of making measurements from photographs. It infers the geometry of a scene from a set of unordered photographs or videos. Photography is the projection of a 3D scene onto a 2D plane, losing depth information. The goal of photogrammetry is to reverse this process.
See the presentation of the pipeline steps.
https://meshroom-manual.readthedocs.io
Overall presentation of the Meshroom software.
Detailed tutorial with a focus on the features of the 2019.1 release.
Overall presentation of the photogrammetry practice with Meshroom.
Overall presentation of the protogrammetry practice with Meshroom and detailed presentation how to do the retolopogy in Blender.
Presentation of the Meshroom software with a focus on using it for Match Moving.
You can create custom pipelines in the user interface and save it as template: File > Advanced > Save As Template
.
You can define the MESHROOM_PIPELINE_TEMPLATES_PATH
environment variable to specific folders to make these pipelines available in Meshroom.
In a standard precompiled version of Meshroom, you can also directly add custom pipelines in lib/meshroom/pipelines
.
You can create custom nodes in python and make them available in Meshroom using the MESHROOM_NODES_PATH
environment variable.
Here is an example to launch a Blender rendering from Meshroom.
In a standard precompiled version of Meshroom, you can also directly add custom nodes in lib/meshroom/nodes
.
To be recognized by Meshroom, a custom folder with nodes should be a Python module (an __init__.py
file is needed).
The project is released under MPLv2, see COPYING.md.
If you use this project for a publication, please cite the paper:
@inproceedings{alicevision2021,
title={{A}liceVision {M}eshroom: An open-source {3D} reconstruction pipeline},
author={Carsten Griwodz and Simone Gasparini and Lilian Calvet and Pierre Gurdjos and Fabien Castan and Benoit Maujean and Gregoire De Lillo and Yann Lanthony},
booktitle={Proceedings of the 12th ACM Multimedia Systems Conference - {MMSys '21}},
doi = {10.1145/3458305.3478443},
publisher = {ACM Press},
year = {2021}
}
You can download pre-compiled binaries for the latest release.
If you want to build it yourself, see INSTALL.md to setup the project and pre-requisites.
Get the source code and install runtime requirements:
git clone --recursive git://github.com/alicevision/meshroom
cd meshroom
pip install -r requirements.txt
You need to have AliceVision installation in your PATH (and LD_LIBRARY_PATH on Linux/macOS).
# Windows
set PYTHONPATH=%CD% && python meshroom/ui
# Linux/macOS
PYTHONPATH=$PWD python meshroom/ui
On Ubuntu, you may have conflicts between native drivers and mesa drivers. In that case, you need to force usage of native drivers by adding them to the LD_LIBRARY_PATH:
LD_LIBRARY_PATH=/usr/lib/nvidia-340 PYTHONPATH=$PWD python meshroom/ui
You may need to adjust the folder /usr/lib/nvidia-340
with the correct driver version.
# Windows: set PYTHONPATH=%CD% &&
# Linux/macOS: PYTHONPATH=$PWD
python bin/meshroom_batch --input INPUT_IMAGES_FOLDER --output OUTPUT_FOLDER
To use Meshroom (ui) without building AliceVision
LD_LIBRARY_PATH=~/foo/Meshroom-2023.2.0/aliceVision/lib/ PATH=$PATH:~/foo/Meshroom-2023.2.0/aliceVision/bin/ PYTHONPATH=$PWD python3 meshroom/ui
PyCharm Community is free IDE which can be used. To start and debug a project with that IDE,
right-click on Meshroom/ui/__main__.py
> Debug
, then Edit Configuration
, in Environment variables
:
PATH=$PATH:/foo/build/Linux-x86_64/
LD_LIBRARY_PATH=/foo/Meshroom-2023.2.0/aliceVision/lib/;PATH=$PATH:/foo/Meshroom-2023.2.0/aliceVision/bin/
(Make sure that you are on the branch matching the right version)See the Meshroom wiki for more information.
Use the public mailing-list to ask questions or request features. It is also a good place for informal discussions like sharing results, interesting related technologies or publications:
[email protected] http://groups.google.com/group/alicevision
You can also contact the core team privately on: [email protected].