ViTPose-Plus-Huge is a large Vision Transformer model for pose estimation developed by the University of Sydney. It detects human keypoints and body poses in images with high accuracy. The model is available via Hugging Face Transformers and supports research and applications in computer vision and human motion analysis.
Vitpose Plus Huge is an Other AI project. Accurate multi-person human pose and keypoint estimation from images using transformer architectures. Vitpose Plus Huge is an open-source project aimed at developers. Vitpose Plus Huge is open source under the Apache-2.0 license. It ships for the web, and it can be self-hosted.
It is developed by University of Sydney (Australia), and it first shipped in 2022. Development happens publicly on GitHub with 2.1k stars. Key capabilities include Pose Estimation, Keypoint Detection, and Vision Transformer.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do