Get 3D pose and shape of people from monocular images
--
Get 3D pose and shape of people from monocular images
THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers
arXiv paper abtract https://arxiv.org/abs/2106.09336
arXiv PDF paper https://arxiv.org/pdf/2106.09336.pdf
… THUNDR, a transformer-based deep neural network … reconstruct the 3d pose and shape of people, given monocular RGB images.
… supports self-supervised regimes, and ensures that solutions are consistent with human anthropometry.
… state-of-the-art results on Human3.6M and 3DPW, for both the fully-supervised and the self-supervised models, for the task of inferring 3d human shape, joint positions, and global translation.
… very solid 3d reconstruction performance for difficult human poses collected in the wild.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
