Video to DensePose is a Hugging Face Space that applies the DensePose model to input videos. It maps human body surfaces in each frame, producing detailed visualizations of body part correspondences. The tool is useful for researchers and developers working on human pose estimation, action recognition, and related computer vision tasks. It runs entirely in the cloud via a simple web interface.
Video to DensePose is a Video generation project. It focuses on extracting dense human pose estimations from video footage for computer vision research and applications. Video to DensePose is an open-source project aimed at computer vision researchers. It is available for free. It ships for the web, and it can be self-hosted.
fffiloni builds and maintains Video to DensePose, and it first shipped in 2023.
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