Related papers: Improving Human Motion Plausibility with Body Mome…

The motion of a compact body in space and time is commonly described by the world line of a point representing the instantaneous position of the body. In General Relativity such a world-line formalism is not quite straightforward because of…

Most of the existing 3D human pose estimation approaches mainly focus on predicting 3D positional relationships between the root joint and other human joints (local motion) instead of the overall trajectory of the human body (global…

Human motion prediction from motion capture data is a classical problem in the computer vision, and conventional methods take the holistic human body as input. These methods ignore the fact that, in various human activities, different body…

In this paper, we present an approach for generating a variety of whole-body motions for a humanoid robot. We extend the available Model Predictive Control (MPC) approaches for walking on flat terrain to plan for both vertical motion of the…

In this work, we present MoLang (a Motion-Language connecting model) for learning joint representation of human motion and language, leveraging both unpaired and paired datasets of motion and language modalities. To this end, we propose a…

Exploring spatial-temporal dependencies from observed motions is one of the core challenges of human motion prediction. Previous methods mainly focus on dedicated network structures to model the spatial and temporal dependencies. This paper…

Active muscles are crucial for maintaining postural stability when seated in a moving vehicle. Advanced active 3D non-linear full body models have been developed for impact and comfort simulation, including large numbers of individual…

This paper discusses video motion capture, namely, 3D reconstruction of human motion from multi-camera images. After the Part Confidence Maps are computed from each camera image, the proposed spatiotemporal filter is applied to deliver the…

Designing an exoskeleton to reduce the risk of low-back injury during lifting is challenging. Computational models of the human-robot system coupled with predictive movement simulations can help to simplify this design process. Here, we…

Temporomandibular joint plays a major role in everyday life allowing speaking and eating. This work aims to describe a method that combine several mechanical tests highlighting soft tissue properties, both local and global, through local…

Human motion prediction has traditionally been framed as a sequence regression problem where models extrapolate future joint coordinates from observed pose histories. While effective over short horizons this approach does not separate…

Existing digital human models approximate the human skeletal system using rigid bodies connected by rotational joints. While the simplification is considered acceptable for legs and arms, it significantly lacks fidelity to model rich torso…

Predicting human mobility is crucial for urban planning, traffic control, and emergency response. Mobility behaviors can be categorized into individual and collective, and these behaviors are recorded by diverse mobility data, such as…

Articulated objects (e.g., doors and drawers) exist everywhere in our life. Different from rigid objects, articulated objects have higher degrees of freedom and are rich in geometries, semantics, and part functions. Modeling different kinds…

Developing feasible body trajectories for legged systems on arbitrary terrains is a challenging task. In this paper, we present a paradigm that allows to design feasible Center of Mass (CoM) and body trajectories in an efficient manner. In…

Human Video Motion Transfer (HVMT) aims to, given an image of a source person, generate his/her video that imitates the motion of the driving person. Existing methods for HVMT mainly exploit Generative Adversarial Networks (GANs) to perform…

Whole-body contact is an effective strategy for improving the stability and efficiency of the motion of robots. For robots to automatically perform such motions, we propose a posture generation method that employs all available surfaces of…

In this paper, we present an efficient form of Volterra's equations of motion for both unconstrained and constrained multibody dynamical systems that include ignorable coordinates. The proposed method is applicable for systems with both…

We revisit the concept of constraint embedding as a means for dealing with kinematic loop constraints during dynamics computations for rigid-body systems. Specifically, we consider the local loop constraints emerging from common actuation…

We introduce MotioNet, a deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video.While previous methods rely on either rigging or inverse kinematics (IK) to associate a consistent skeleton with…