AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |
Back to Blog
Skin skeleton3/12/2024 ![]() ![]() ![]() By fitting SKEL to SMPL meshes we are able to “upgrade" existing human pose and shape datasets to include biomechanical parameters. We show that SKEL has more biomechanically accurate joint locations than SMPL, and the bones fit inside the body surface better than previous methods. The resulting SKEL model is animatable like SMPL but with fewer, and biomechanically-realistic, degrees of freedom. Finally, we re-parametrize the SMPL mesh with the new kinematic parameters. ![]() We then learn a regressor from SMPL mesh vertices to the optimized joint locations and bone rotations. We build such a dataset by optimizing biomechanically accurate skeletons inside SMPL meshes from AMASS sequences. To enable this, we need training data of skeletons inside SMPL meshes in diverse poses. To that end, we develop SKEL, which re-rigs the SMPL body model with a biomechanics skeleton. What is needed is a parametric 3D human model with a biomechanically accurate skeletal structure that can be easily posed. On the other hand, methods for estimating biomechanically accurate skeletal motion typically rely on complex motion capture systems and expensive optimization methods. ![]() However, existing body models have simplified kinematic structures that do not correspond to the true joint locations and articulations in the human skeletal system, limiting their potential use in biomechanics. Great progress has been made in estimating 3D human pose and shape from images and video by training neural networks to directly regress the parameters of parametric human models like SMPL. ![]()
0 Comments
Read More
Leave a Reply. |