Get 3D shape, pose, and relative depth of people from a single image despite occlusion
Get 3D shape, pose, and relative depth of people from a single image despite occlusion
Putting People in their Place: Monocular Regression of 3D People in Depth
arXiv paper abstract https://arxiv.org/abs/2112.08274
arXiv PDF paper https://arxiv.org/pdf/2112.08274.pdf
Given an image with multiple people, our goal is to directly regress the pose and shape of all the people as well as their relative depth.
… First … develop a novel method to infer the poses and depth of multiple people in a single image.
… method, called BEV, adds an additional imaginary Bird’s-Eye-View representation to explicitly reason about depth.
BEV reasons simultaneously about body centers in the image and in depth and, by combing these, estimates 3D body position.
… exploit a 3D body model space that lets BEV infer shapes from infants to adults.
… BEV outperforms existing methods on depth reasoning, child shapeestimation, and robustness to occlusion. …
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
