Related papers: FootFormer: Estimating Stability from Visual Input

Human motion synthesis is an important problem with applications in graphics, gaming and simulation environments for robotics. Existing methods require accurate motion capture data for training, which is costly to obtain. Instead, we…

In this paper, we propose a global method for estimating the motion of a camera which films a static scene. Our approach is direct, fast and robust, and deals with adjacent frames of a sequence. It is based on a quadratic approximation of…

As bipedal robots become more and more popular in commercial and industrial settings, the ability to control them with a high degree of reliability is critical. To that end, this paper considers how to accurately estimate which feet are…

Real-time human motion reconstruction from a sparse set of (e.g. six) wearable IMUs provides a non-intrusive and economic approach to motion capture. Without the ability to acquire position information directly from IMUs, recent works took…

In many applications of advanced robotic manipulation, six degrees of freedom (6DoF) object pose estimates are continuously required. In this work, we develop a multi-modality tracker that fuses information from visual appearance and…

Crowd movement simulation is crucial for pedestrian safety management and facility design. Data-driven models offer the potential to improve realism and predictive accuracy, but most are developed for a single scenario, limiting their…

Estimating human motion from video is an active research area due to its many potential applications. Most state-of-the-art methods predict human shape and posture estimates for individual images and do not leverage the temporal information…

Humanoid parkour requires locomotion policies to coordinate whole-body dynamics across rapidly changing terrains such as stairs, gaps, slopes, and obstacles. Existing reinforcement learning policies are largely reactive, mapping…

Human motion is fundamentally driven by continuous physical interaction with the environment. Whether walking, running, or simply standing, the forces exchanged between our feet and the ground provide crucial insights for understanding and…

Visual object tracking (VOT) is an essential component for many applications, such as autonomous driving or assistive robotics. However, recent works tend to develop accurate systems based on more computationally expensive feature…

Mobile applications and on-body devices are becoming increasingly ubiquitous tools for physical activity tracking. We propose utilizing a self-tracker's habits to support continuous prediction of whether they will reach their daily step…

While current methods have shown promising progress on estimating 3D human motion from monocular videos, their motion estimates are often physically unrealistic because they mainly consider kinematics. In this paper, we introduce…

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…

Change detection in remote sensing imagery is essential for a variety of applications such as urban planning, disaster management, and climate research. However, existing methods for identifying semantically changed areas overlook the…

The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model…

Trajectory prediction in autonomous driving relies on accurate representation of all relevant contexts of the driving scene, including traffic participants, road topology, traffic signs, as well as their semantic relations to each other.…

Learning 3D human motion from 2D inputs is a fundamental task in the realms of computer vision and computer graphics. Many previous methods grapple with this inherently ambiguous task by introducing motion priors into the learning process.…

The pursuit of controllability as a higher standard of visual content creation has yielded remarkable progress in customizable image synthesis. However, achieving controllable video synthesis remains challenging due to the large variation…

Accurate single-object tracking and short-term motion forecasting remain challenging under occlusion, scale variation, and temporal drift, which disrupt the temporal coherence required for real-time perception. We introduce…

Identifying the physical properties of the surrounding environment is essential for robotic locomotion and navigation to deal with non-geometric hazards, such as slippery and deformable terrains. It would be of great benefit for robots to…