From video get 3D shape of people, animals, and other non-rigid objects

From video get 3D shape of people, animals, and other non-rigid objects

3D Reconstruction from Videos: LASR
Generate 3D models of humans or animals moving from only a short video as input.
Towards AI https://pub.towardsai.net/3d-reconstruction-from-videos-lasr-c29459399aed

LASR: Learning Articulated Shape Reconstruction from a Monocular Video
Project Web site https://lasr-google.github.io
arXiv paper abstract https://arxiv.org/abs/2105.02976
arXiv PDF paper https://arxiv.org/pdf/2105.02976.pdf

… challenging to reconstruct nonrigid structures from RGB inputs, due to its under-constrained nature.
… In this work, we introduce a template-free approach to learn 3D shapes from a single video. It adopts an analysis-by-synthesis strategy that forward-renders object silhouette, optical flow, and pixel values to compare with video observations, which generates gradients to adjust the camera, shape and motion parameters. Without using a category-specific shape template, our method faithfully reconstructs nonrigid 3D structures from videos of human, animals, and objects of unknown classes. …

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