Surround-view fisheye cameras are commonly used for near-field sensing in automated
driving. Four fisheye cameras on four sides of the vehicle are sufficient to cover 360° around …

Abstract We present Ego-Exo4D a diverse large-scale multimodal multiview video dataset
and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric …

Due to the increasingly high proportion of manual activities in production processes, there is
a constant risk of musculoskeletal disorders or work-related injuries. The risk of these …

We present the first real-time method to capture the full global 3D skeletal pose of a human
in a stable, temporally consistent manner using a single RGB camera. Our method combines …

We address the highly challenging problem of real-time 3D hand tracking based on a
monocular RGB-only sequence. Our tracking method combines a convolutional neural …

Human gait analysis is often conducted in clinical and basic research, but many common
approaches (eg, three-dimensional motion capture, wearables) are expensive, immobile …

Estimating human pose, shape, and motion from images and video are fundamental
challenges with many applications. Recent advances in 2D human pose estimation use …

We propose a CNN-based approach for 3D human body pose estimation from single RGB
images that addresses the issue of limited generalizability of models trained solely on the …

We present a real-time approach for multi-person 3D motion capture at over 30 fps using a
single RGB camera. It operates successfully in generic scenes which may contain …

Abstract We introduce the Aria Digital Twin (ADT)-an egocentric dataset captured using Aria
glasses with extensive object, environment, and human level ground truth. This ADT release …