openpose
mmpose
Our great sponsors
| openpose | mmpose | |
|---|---|---|
| 36 | 31 | |
| 29,802 | 4,969 | |
| 1.3% | 4.2% | |
| 5.2 | 8.4 | |
| 9 days ago | 22 days ago | |
| C++ | Python | |
| GNU General Public License v3.0 or later | Apache License 2.0 |
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.
openpose
-
AI "Artists" Are Lazy, and the Ultimate Goal of AI Image Generation (hint: its sloth)
Open Pose, a multi-person keypoint detection library for body, face, hands, and foot estimation [10], is used for posing generated characters;
-
Analyze defects and errors in the created images
OpenPose
-
[D] Which open source models can replicate wonder dynamics's drag'n'drop cg characters?
Perhaps something like OpenPose for pose estimation?
-
Do we have Locally Run AI mocap yet?
OpenPose looks like what you're looking for, it seems to have plugins for Unity. I can't say I've used it though.
-
Let's take a break!
You are correct. Open Pose has two keypoints for the eyes and two more for the ears. By saying were the ears are you automatically influence the angle of the head. You can see more about it on this github page. Just scroll a tiny bit and you can see a gif of the nodes overlapped on humans
-
Accelerate Machine Learning Local Development and Test Workflows with Nvidia Docker
FROM nvidia/cuda:10.0-cudnn7-devel-ubuntu18.04 # https://hub.docker.com/r/nvidia/cuda ENV DEBIAN_FRONTEND=noninteractive # install the dependencies for building OpenPose RUN apt-get update && # The rest is ignored for brevity. RUN pip3 install --no-cache-dir # The rest is ignored for brevity. # install cmake, clone OpenPose and download models RUN wget https://cmake.org/files/v3.20/cmake-3.20.2-linux-x86_64.tar.gz && \ # The rest is ignored for brevity. WORKDIR /openpose/build RUN alias python=python3 && cmake -DBUILD_PYTHON=OFF -DWITH_GTK=OFF -DUSE_CUDNN=ON .. # Build OpenPose. Cudnn 8 causes memory issues this is why we are using base with CUDA 10 and Cudnn 7 # Fix for CUDA 10.0 and Cudnn 7 based on the post below. # https://github.com/CMU-Perceptual-Computing-Lab/openpose/issues/1753#issuecomment-792431838 RUN sed -ie 's/set(AMPERE "80 86")/#&/g' ../cmake/Cuda.cmake && \ sed -ie 's/set(AMPERE "80 86")/#&/g' ../3rdparty/caffe/cmake/Cuda.cmake && \ make -j`nproc` && \ make install WORKDIR /openpose
- nub needs some directions
-
full body tracking with WiFi signals by utilizing deep learning architectures
One of the best cam only libraries (no depth sensor) I've seen is openpose, I ran it through a 360 camera and it was able to track body, face, and fingers really well even with spherical distortion from the 360 cam. example 360
- How to do body tracking for (real) camera
- How to get rotation (yaw/pitch/roll) from face detection keypoints?
mmpose
-
RTMPose: The All-In-One Real-time Pose Estimation Solution for R&D
RTMPose-m achieves 75.8% AP on COCO with 90+ FPS on an Intel i7-11700 CPU and 430+ FPS on an NVIDIA GTX 1660 Ti GPU, and RTMPose-l achieves 67.0% AP on COCO-WholeBody with 130+ FPS.
-
MMDeploy: Deploy All the Algorithms of OpenMMLab
MMPose: OpenMMLab pose estimation toolbox and benchmark.
-
Model conversion from Pytorch to Tf using Onnx.
I downloaded pytorch2onnx.py from mmPose tools. It's big, but the top half is imports and input arguments. Line 125, I hard-coded my (image) input size. I ran it on my .pth model file, and out pop'd an onnx file.
-
Finetuning Openpose for custom dataset
They have a specific repo called mmpose: https://github.com/open-mmlab/mmpose
-
State of the art 2D body pose estimation [Discussion]
I would start with mmpose. It's basically a curated list of the best models ready to go.
-
[P] Object detection framework : Detectron2 VS MMDetection
The [MMLab key point detection](https://github.com/open-mmlab/mmpose) is in a separate repo from detection.
-
[D] Searching for open source pose estimation solution similar to open pose ?
One option is mmPose. They have a bunch of 2D/3D models implemented and support different skeleton structures.
-
Human Pose Estimation Recommendation
This library is pretty good. It has implementations for a number of pose estimators. I think Darkpose is the best one from memory
-
Human pose classification problem.
Check out https://github.com/open-mmlab/mmpose I think they have guides for new datasets
What are some alternatives?
mediapipe - Cross-platform, customizable ML solutions for live and streaming media.
openpifpaf - Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
AlphaPose - Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
detectron2 - Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
mmaction2 - OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
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.
deep-high-resolution-net.pytorch - The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
BlazePose-tensorflow - A third-party Tensorflow Implementation for paper "BlazePose: On-device Real-time Body Pose tracking".
AdelaiDet - AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.
MocapNET - We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance
mmfewshot - OpenMMLab FewShot Learning Toolbox and Benchmark