Capturing and inferring dense full-body human-scene contact

CHP Huang, H Yi, M Höschle… - Proceedings of the …, 2022 - openaccess.thecvf.com
Inferring human-scene contact (HSC) is the first step toward understanding how humans
interact with their surroundings. While detecting 2D human-object interaction (HOI) and …

Avatars grow legs: Generating smooth human motion from sparse tracking inputs with diffusion model

Y Du, R Kips, A Pumarola, S Starke… - Proceedings of the …, 2023 - openaccess.thecvf.com
With the recent surge in popularity of AR/VR applications, realistic and accurate control of
3D full-body avatars has become a highly demanded feature. A particular challenge is that …

Avatarposer: Articulated full-body pose tracking from sparse motion sensing

J Jiang, P Streli, H Qiu, A Fender, L Laich… - European conference on …, 2022 - Springer
Abstract Today's Mixed Reality head-mounted displays track the user's head pose in world
space as well as the user's hands for interaction in both Augmented Reality and Virtual …

Questsim: Human motion tracking from sparse sensors with simulated avatars

A Winkler, J Won, Y Ye - SIGGRAPH Asia 2022 Conference Papers, 2022 - dl.acm.org
Real-time tracking of human body motion is crucial for interactive and immersive
experiences in AR/VR. However, very limited sensor data about the body is available from …

Ego-body pose estimation via ego-head pose estimation

J Li, K Liu, J Wu - Proceedings of the IEEE/CVF Conference …, 2023 - openaccess.thecvf.com
Estimating 3D human motion from an egocentric video sequence plays a critical role in
human behavior understanding and has various applications in VR/AR. However, naively …

Transformer inertial poser: Real-time human motion reconstruction from sparse imus with simultaneous terrain generation

Y Jiang, Y Ye, D Gopinath, J Won, AW Winkler… - SIGGRAPH Asia 2022 …, 2022 - dl.acm.org
Real-time human motion reconstruction from a sparse set of (eg six) wearable IMUs
provides a non-intrusive and economic approach to motion capture. Without the ability to …

Flag: Flow-based 3d avatar generation from sparse observations

S Aliakbarian, P Cameron, F Bogo… - Proceedings of the …, 2022 - openaccess.thecvf.com
To represent people in mixed reality applications for collaboration and communication, we
need to generate realistic and faithful avatar poses. However, the signal streams that can be …

Bodiffusion: Diffusing sparse observations for full-body human motion synthesis

A Castillo, M Escobar, G Jeanneret… - Proceedings of the …, 2023 - openaccess.thecvf.com
Mixed reality applications require tracking the user's full-body motion to enable an
immersive experience. However, typical head-mounted devices can only track head and …

A Survey on 3D Egocentric Human Pose Estimation

MM Azam, K Desai - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Egocentric human pose estimation aims to estimate human body poses and develop body
representations from a first-person camera perspective. It has gained vast popularity in …

Combining Motion Matching and Orientation Prediction to Animate Avatars for Consumer‐Grade VR Devices

JL Ponton, H Yun, C Andujar… - Computer Graphics …, 2022 - Wiley Online Library
The animation of user avatars plays a crucial role in conveying their pose, gestures, and
relative distances to virtual objects or other users. Self‐avatar animation in immersive VR …