SuperGluePretrainedNetwork
DeepLabCut
Our great sponsors
SuperGluePretrainedNetwork | DeepLabCut | |
---|---|---|
5 | 12 | |
2,906 | 4,283 | |
0.0% | 2.2% | |
0.0 | 8.7 | |
over 1 year ago | 11 days ago | |
Python | Python | |
GNU General Public License v3.0 or later | GNU Lesser General Public License v3.0 only |
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
DeepLabCut
-
Landmark tracking / Pose estimation model training in TensorFlow :
Use DeepLabCut, I also strongly suggest that you should fund their work: https://github.com/DeepLabCut/DeepLabCut
-
DeepLabCut alternatives - leap, DeepPoseKit, APT, sleap, and anipose
6 projects | 15 Jul 2022
-
Help: Using CV to recognize angles and lines from a picture
DeepLabCut is also worth mentioning here
-
Backyard AI dog poop detector walkthrough
1 - Detecting the dog's body parts was the most difficult portion of this, and thankfully I stumbled upon DeepLabCut (https://github.com/DeepLabCut/DeepLabCut) which enables training a model to track a specific animal(s) posture. In the video, this is basically the dots that are overlayed on top of the dog, and follower her around. DeepLabCut is basically just saying that this is where it thinks it recognizes "spine" and "tail".
-
Built a dog poop detector for my backyard
I used https://github.com/DeepLabCut/DeepLabCut for the core dog tracking capability, then I wrote the code that analyzes the posture (output by the model, trained via DeepLabCut) of the dog.
I built a dog poop detector for my backyard using DeepLabCut (https://github.com/DeepLabCut/DeepLabCut) and some janky poop detection heuristics I wrote that processed on the detected posture of my dog, if it's in the frame of my security camera. If it detects my dog pooping, it will record the location in a CSV and draw all the locations on an up to date image of my backyard.
-
[P] Built a dog poop detector for my backyard
Also, check out DeepLabCut. My project wouldn't have been possible without it, and it's really cool: https://github.com/DeepLabCut/DeepLabCut
-
I want to create a pill counter using points instead of bounding boxes. What model should I train from?
Well you could try DeepLabCut - https://github.com/DeepLabCut/DeepLabCut
- DeepLabCut: Deep-learning based markerless pose estimation for all animals
- Can AI make 3d model using my 2d photos ?
What are some alternatives?
LoFTR - Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022
DeepPoseKit - a toolkit for pose estimation using deep learning
ORB_SLAM3 - ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
yolov5 - YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
nerfmm - (Arxiv 2021) NeRF--: Neural Radiance Fields Without Known Camera Parameters
lightweight-human-pose-estimation.pytorch - Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
torchdrug - A powerful and flexible machine learning platform for drug discovery
sleap - A deep learning framework for multi-animal pose tracking.
dgl - Python package built to ease deep learning on graph, on top of existing DL frameworks.
OpenCV - Open Source Computer Vision Library
open_vins - An open source platform for visual-inertial navigation research.
Hekate-Toolbox - A toolbox for Hekate