Second, human shape is highly correlated with gender, but existing work ignores this.
Ranked #1 on 3D Multi-Person Mesh Recovery on AGORA
Second, we show that POSA's learned representation of body-scene interaction supports monocular human pose estimation that is consistent with a 3D scene, improving on the state of the art.
Training computers to understand, model, and synthesize human grasping requires a rich dataset containing complex 3D object shapes, detailed contact information, hand pose and shape, and the 3D body motion over time.
To understand how people look, interact, or perform tasks, we need to quickly and accurately capture their 3D body, face, and hands together from an RGB image.
Therefore, we develop a dataset of multi-human optical flow and train optical flow networks on this dataset.
To motivate this, we show that current 3D human pose estimation methods produce results that are not consistent with the 3D scene.
Here we explore two variations of synthetic data for this challenging problem; a dataset with purely synthetic humans and a real dataset augmented with synthetic humans.
Previous work has made significant progress towards reconstruction of hand poses and object shapes in isolation.
We use the new method, SMPLify-X, to fit SMPL-X to both controlled images and images in the wild.
Ranked #3 on 3D Human Reconstruction on AGORA
In this work, we propose a framework for hand tracking that can capture the motion of two interacting hands using only a single, inexpensive RGB-D camera.
Although commercial and open-source software exist to reconstruct a static object from a sequence recorded with an RGB-D sensor, there is a lack of tools that build rigged models of articulated objects that deform realistically and can be used for tracking or animation.
Hand motion capture is a popular research field, recently gaining more attention due to the ubiquity of RGB-D sensors.