SuperGluePretrainedNetwork
aquamam
Our great sponsors
SuperGluePretrainedNetwork | aquamam | |
---|---|---|
5 | 3 | |
2,906 | 1 | |
0.0% | - | |
0.0 | 3.6 | |
over 1 year ago | 7 months ago | |
Python | Python | |
GNU General Public License v3.0 or later | MIT License |
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.
SuperGluePretrainedNetwork
-
SuperGlue is a CVPR2022 research project done at Magicleap for pose estimation in real-world environments. Check out the tool link in the comments
Code: https://github.com/magicleap/SuperGluePretrainedNetwork
-
Advances in SLAM since 2016
This basically includes a deep learning based approach to do keypoint detection, and match them across image frames. This includes papers like SuperPoint, Superglue, and more. There is also a way to do dense matching with neural networks.
- [D] Solo machine learning engineer woes
-
How to train a CNN for a map localization task?
Feature matching is the way to go imo. Try out OpenCV's inbuilt feature matching methods like SIFT and FLANN. If the performance is poor, you can even try out CNN aided matching algos like SuperGlue Link (CVPR2020)
-
What is the SOTA for feature extraction / description / matching ?
SIFT and brute force matching is your best bet in classical computer vision if you're unconcerned with runtime. There are methods from deep learning that can perform better, somewhat domain dependent. Check out superpoint and superglue from magic leap. https://github.com/magicleap/SuperGluePretrainedNetwork
aquamam
-
DeepVoxels: Learning Persistent 3D Feature Embeddings
This paper is near and dear to my heart because I saw the presentation at the first and only machine learning conference I've ever attended (thanks a lot, ICML, NeurIPS (x2), and ICLR!). It's a neural rendering approach that precedes NeRF, but you can see some similarities (even more so in the follow-up paper about "Scene Representation Networks"). Sitzmann and co-authors also published a paper about using sinusoidal activations in implicit representation models at NeurIPS 2020, the same conference where the "Fourier Features" paper (which has many of the same authors as the NeRF paper) was also presented. It's always interesting to me to see how ideas in science often pop-up at the same time from different researchers (e.g., attention).
- AQuaMaM: An Autoregressive, Quaternion Manifold Model for Rapidly Estimating Complex SO(3) Distributions
-
[R] AQuaMaM: An Autoregressive, Quaternion Manifold Model for Rapidly Estimating Complex SO(3) Distributions
Code for the paper can be found here.
What are some alternatives?
LoFTR - Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022
openpifpaf - Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
ORB_SLAM3 - ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
Hierarchical-Localization - Visual localization made easy with hloc
nerfmm - (Arxiv 2021) NeRF--: Neural Radiance Fields Without Known Camera Parameters
baller2vec - A multi-entity Transformer for multi-agent spatiotemporal modeling.
torchdrug - A powerful and flexible machine learning platform for drug discovery
ailia-models - The collection of pre-trained, state-of-the-art AI models for ailia SDK
dgl - Python package built to ease deep learning on graph, on top of existing DL frameworks.
baller2vecplusplus - A look-ahead multi-entity Transformer for modeling coordinated agents.
DeepLabCut - Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans