Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
KAPAO is an efficient single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.
| Date | Stars |
|---|---|
| 2026-07-24 | 770 |
| 2026-07-25 | 770 |
| 2026-07-28 | 770 |
| 2026-07-30 | 770 |
| 2026-08-06 | 770 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# KAPAO (Keypoints and Poses as Objects) [Accepted to ECCV 2022](https://arxiv.org/abs/2111.08557) KAPAO is an efficient single-stage multi-person human pose estimation method that models **k**eypoints **a**nd **p**oses **a**s **o**bjects within a dense anchor-based detection framework. KAPAO simultaneously detects _pose objects_ and _keypoint objects_ and fuses the detections to predict human poses:  When not using test-time augmentation (TTA), KAPAO is much faster and more accurate than previous single-stage methods like [DEKR](https://github.com/HRNet/DEKR), [HigherHRNet](https://github.com/HRNet/HigherHRNet-Human-Pose-Estimation), [HigherHRNet + SWAHR](https://github.com/greatlog/SWAHR-HumanPose), and [CenterGroup](https://github.com/dvl-tum/center-group):  This repository contains the official PyTorch implementation for the paper: <br> Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation. Our code was forked from ultralytics/yolov5 at commit [5487451](https://github.com/ultralytics/yolov5/tree/5487451). ### Setup 1. If you haven't already, [install Anaconda or Miniconda](https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html). 2. Create a new conda environment with Python 3.6: `$ conda create -n kapao python=3.6`. 3. Activate the environment: `$ conda activate kapao` 4. Clone this repo: `$ git clone https://github.com/wmcnally/kapao.git` 5. Install the dependencies: `$ cd kapao && pip install -r requirements.txt` 6. Download the trained models: `$ python data/scripts/download_models.py` ## Inference Demos **Note:** FPS calculations include **all processing** (i.e., including image loading, resizing, inference, plotting / tracking, etc.). See script arguments for inference options. --- #### Static Image To generate the four images in the GIF above: 1. `$ python demos/image.py --bbox` 2. `$ python demos/image.py --bbox --pose --face --no-kp-dets` 3. `$ python demos/image.py --bbox --pose --face --no-kp-dets --kp-bbox` 4. `$ python demos/image.py --pose --face` #### Shuffling Video KAPAO runs fastest on low resolution video with few people in the frame. This demo runs KAPAO-S on a single-person 480p dance video using an input size of 1024. The inference speed is **~9.5 FPS** on our CPU, and **~60 FPS** on our TITAN Xp. **CPU inference:**<br> <br> To display the results in real-time: <br> `$ python demos/video.py --face --display` To create the GIF above:<br> `$ python demos/video.py --face --device cpu --gif` **CPU specs:**<br> Intel Core i7-8700K<br> 16GB DDR4 3000MHz<br> Samsung 970 Pro M.2 NVMe SSD<br> --- #### Flash Mob Video This demo runs KAPAO-S on a 720p flash mob video using an input size of 1280. **GPU inference:**<br> <br> To display the results in real-time: <br> `$ python demos/video.py --yt-id 2DiQUX11YaY --tag 136 --imgsz 1280 --color 255 0 255 --start 188 --end 196 --display` To create the GIF above:<br> `$ python demos/video.py --yt-id 2DiQUX11YaY --tag 136 --imgsz 1280 --color 255 0 255 --start 188 --end 196 --gif` --- #### Red Light Green Light This demo runs KAPAO-L on a 480p clip from the TV show _Squid Game_ using an input size of 1024. The plotted poses constitute keypoint objects only. **GPU inference:**<br> <br> To display the results in real-time:<br> `$ python demos/video.py --yt-id nrchfeybHmw --imgsz 1024 --weights kapao_l_coco.pt --conf-thres-kp 0.01 --kp-obj --face --start 56 --end 72 --display` To create the GIF above:<br> `$ python demos/video.py --yt-id nrchfeybHmw --imgsz 1024 --weights kapao_l_coco.pt --conf-thres-kp 0.01 --kp-obj --face --start 56 --end 72 --gif` --- #### Squash Video This demo runs KAPAO-S on a 1080p slow motio
Excerpt of 10,665 characters
Read on GitHub
Glenn Jocher · @ultralytics · United States
1.1k
278
Alex Stoken · Amentum JETS II @ NASA Johnson Space Center · Azerbaijan
34
Ayush Chaurasia · India
29
Jirka Borovec · Czech Republic
27
20
Yonghye Kwon · MarkAny · South Korea
9
Lorna · NVIDIA Corporation
7
Abhiram V · @zealabs
5
tkianai · 别怕失败，大不了从头来过 · China
4
Jing Qiu · China
4
Piotr Skalski · @roboflow
4
4
3
imyhxy · China
3
Jiacong Fang
3
3
2
2
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3c46222bf43f6edf, topic:yolo, topic:pose-estimation, desc:pose estimation
matched fp:3c46222bf43f6edf, topic:deep-learning, topic:pytorch