3D human pose and shape estimation
27 papers with code • 1 benchmarks • 2 datasets
Estimate 3D human pose and shape (e.g. SMPL) from images
Top-down methods dominate the field of 3D human pose and shape estimation, because they are decoupled from human detection and allow researchers to focus on the core problem.
HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation
We show that HybrIK preserves both the accuracy of 3D pose and the realistic body structure of the parametric human model, leading to a pixel-aligned 3D body mesh and a more accurate 3D pose than the pure 3D keypoint estimation methods.
With a comprehensive set of experiments, we show how this data can be used to train discriminative models that produce results with an unprecedented level of detail: our models predict 31 segments and 91 landmark locations on the body.
Image-based features are attached to the mesh vertices and the Graph-CNN is responsible to process them on the mesh structure, while the regression target for each vertex is its 3D location.
Two common approaches to deal with low-resolution images are applying super-resolution techniques to the input, which may result in unpleasant artifacts, or simply training one model for each resolution, which is impractical in many realistic applications.
Regression-based methods have recently shown promising results in reconstructing human meshes from monocular images.
We present a novel human body model formulated by an extensive set of anthropocentric measurements, which is capable of generating a wide range of human body shapes and poses.
Reconstructing 3D human shape and pose from monocular images is challenging despite the promising results achieved by the most recent learning-based methods.
We describe a physics-based method that simulates human bodies at rest in a bed with a pressure sensing mat, and present PressurePose, a synthetic dataset with 206K pressure images with 3D human poses and shapes.