pixel-perfect-sfm
Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award) (by cvg)
voxblox
A library for flexible voxel-based mapping, mainly focusing on truncated and Euclidean signed distance fields. (by ethz-asl)
pixel-perfect-sfm | voxblox | |
---|---|---|
4 | 1 | |
1,246 | 1,255 | |
1.8% | 1.0% | |
4.2 | 0.0 | |
about 2 months ago | 2 months ago | |
C++ | C++ | |
Apache License 2.0 | BSD 3-clause "New" or "Revised" License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
pixel-perfect-sfm
Posts with mentions or reviews of pixel-perfect-sfm.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-06-07.
-
On replacing Colmap
Are there alternatives available to the SfM pipeline? https://github.com/cvg/pixel-perfect-sfm for instance takes a deep NN to predict surfaces in the dense step ( not needed for GSplats), is a trained approach for spare reconstruction thinkable, are there other SfM methods that are significantly faster or find more features?
-
[advice] lost in the field
If you are interested in camera pose estimation from images, then the state of the art baseline is still Colmap which is used by industry and research. You can checkout concurrent work like https://github.com/cvg/pixel-perfect-sfm. Should be a lot of tutorials and documentation for you to get it running.
-
Photometric Bundle Adjustment library?
Finally there is also https://github.com/cvg/pixel-perfect-sfm which does do some photometric/dense refinement, but I think it only works in the featuremetric space. So not exactly photometric.
-
Questions for SLAM/SfM for Dense 3D Reconstruction (DSO vs ORB, Monofusion etc.)
I've stumbled upon this and that using DL, and will try to check to simultaneously evaluate them next to developing something using pySLAM. At least that's the current plan.
voxblox
Posts with mentions or reviews of voxblox.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-03-11.
-
Questions for SLAM/SfM for Dense 3D Reconstruction (DSO vs ORB, Monofusion etc.)
For instance you could go with : https://github.com/ov2slam/ov2slam , add some processing on the keyframes for depth maps computation and then fuse the depth maps in a TSDF using https://github.com/personalrobotics/OpenChisel or https://github.com/ethz-asl/voxblox
What are some alternatives?
When comparing pixel-perfect-sfm and voxblox you can also consider the following projects:
colmap - COLMAP - Structure-from-Motion and Multi-View Stereo
elevation_mapping - Robot-centric elevation mapping for rough terrain navigation
OpenChisel - An open-source version of the Chisel chunked TSDF library.
ov2slam - OVĀ²SLAM is a Fully Online and Versatile Visual SLAM for Real-Time Applications
pyslam - pySLAM contains a monocular Visual Odometry (VO) pipeline in Python. It supports many modern local features based on Deep Learning.
MegBA - MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment
MonoRec - Official implementation of the paper: MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera (CVPR 2021)