Vitpose Plus Large
Vitpose Plus Large is a Vision Transformer model for keypoint detection hosted on Hugging Face by the University of Sydney. It forms part of the ViTPose family and addresses the task of locating human body keypoints in images.
The model is provided as a set of weights and associated code that can be loaded through the Transformers library. Users instantiate an AutoImageProcessor and a VitPoseForPoseEstimation class directly from the repository identifier usyd-community/vitpose-plus-large. It supports inference on local hardware or through compatible inference providers and is distributed with both model card documentation and example notebooks for Google Colab and Kaggle.
The repository lists two associated arXiv papers (2204.12484 and 2212.04246) that describe the underlying ViTPose approach. It carries an Apache-2.0 license, making the weights and code openly available for modification and redistribution. The page classifies the work under the keypoint detection task and the Transformers architecture while indicating use of the Safetensors format for the model files.
Open SourceApache-2.0WebAPI
2.1kstars
266forks
2alternatives
3features
2022since
Overview
3 featuresVitpose Plus Large sits in PulseGate's Other AI category. It focuses on detecting human body keypoints and estimating poses from images. It is built as an open-source project for computer vision researchers and developers. The project is open source (Apache-2.0). It runs on the web and API.
Behind Vitpose Plus Large is University of Sydney, and it first shipped in 2022. The project is developed in the open on GitHub with 2.1k stars. Key capabilities include Pose Estimation, Keypoint Detection, and Vision Transformer. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
- Pose Estimation
- Keypoint Detection
- Vision Transformer
Tags
pose-estimationkeypoint-detectionvitposehuman-pose
AI capabilities
Inference: LocalWeights: Open
Built with & integrations
Hosting
AWS
AI providers
local_oss
Connectors
API
Runs on
BrowserAPI-only
Detected from
- AWS
- x-amz-cf-id header · x-amz-cf-pop header · via header
- local_oss
- huggingface in the HTML
Trust & compliance
License
Apache-2.0
Verified signals
Indexing history
1What PulseGate has recorded for this listing
- Indexed22 Jul · 13:49 UTCusyd-community/vitpose-plus-large verified against its public sourceSource: PulseGate · Open
Frequently asked questions about Vitpose Plus Large
- What is Vitpose Plus Large?
- Vitpose Plus Large focuses on detecting human body keypoints and estimating poses from images. It is catalogued under Other AI on PulseGate.
- Who is Vitpose Plus Large for?
- Vitpose Plus Large is an open-source project built for computer vision researchers and developers.
- Does Vitpose Plus Large have a free plan?
- Yes — Vitpose Plus Large is open source under the Apache-2.0 license and free to use.
- What platforms does Vitpose Plus Large run on?
- Vitpose Plus Large runs on the web and API.
- Is Vitpose Plus Large still active?
- Unverified. Vitpose Plus Large has not been re-checked since it entered the index, so there is no finding either way — and only a positive finding would say otherwise.
- What are alternatives to Vitpose Plus Large?
- Similar projects tracked by PulseGate include Vitpose Plus Huge, Vitpose Plus Base, and Vitpose Base Simple.Vitpose Plus HugeVitpose Plus BaseVitpose Base Simple
- Who makes Vitpose Plus Large?
- Vitpose Plus Large is developed by University of Sydney.
- How long has Vitpose Plus Large been around?
- Vitpose Plus Large first shipped in 2022.
Similar apps
Closest matches by what these projects do