ViTPose Plus is a vision transformer-based model for keypoint detection and human pose estimation. Developed by the University of Sydney, it provides strong baselines for pose-related computer vision tasks. The model is available on Hugging Face with Transformers integration for easy loading and inference in research and application development.
Vitpose Plus Base sits in PulseGate's Other AI category. Accurately estimating human body keypoints and poses from images using vision transformers. Vitpose Plus Base is an open-source project aimed at computer vision researchers and developers. Vitpose Plus Base is open source under the Apache-2.0 license. It runs on the web and API.
University of Sydney builds and maintains Vitpose Plus Base, and it first shipped in 2022. Development happens publicly on GitHub with 2.1k stars. Key capabilities include Keypoint Detection, Pose Estimation, and Transformer Architecture.
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