Interdiff: Generating 3d human-object interactions with physics-informed diffusion

S Xu, Z Li, YX Wang, LY Gui - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
This paper addresses a novel task of anticipating 3D human-object interactions (HOIs). Most
existing research on HOI synthesis lacks comprehensive whole-body interactions with …

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 …

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 …

Emdb: The electromagnetic database of global 3d human pose and shape in the wild

M Kaufmann, J Song, C Guo, K Shen… - Proceedings of the …, 2023 - openaccess.thecvf.com
We present EMDB, the Electromagnetic Database of Global 3D Human Pose and Shape in
the Wild. EMDB is a novel dataset that contains high-quality 3D SMPL pose and shape …

Nymeria: A massive collection of multimodal egocentric daily motion in the wild

L Ma, Y Ye, F Hong, V Guzov, Y Jiang… - … on Computer Vision, 2024 - Springer
We introduce Nymeria-a large-scale, diverse, richly annotated human motion dataset
collected in the wild with multiple multimodal egocentric devices. The dataset comes with a) …

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 …

Egolocate: Real-time motion capture, localization, and map** with sparse body-mounted sensors

X Yi, Y Zhou, M Habermann, V Golyanik… - ACM Transactions on …, 2023 - dl.acm.org
Human and environment sensing are two important topics in Computer Vision and Graphics.
Human motion is often captured by inertial sensors, while the environment is mostly …

Ultra inertial poser: Scalable motion capture and tracking from sparse inertial sensors and ultra-wideband ranging

R Armani, C Qian, J Jiang, C Holz - ACM SIGGRAPH 2024 Conference …, 2024 - dl.acm.org
While camera-based capture systems remain the gold standard for recording human motion,
learning-based tracking systems based on sparse wearable sensors are gaining popularity …

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 …

MANIKIN: biomechanically accurate neural inverse kinematics for human motion estimation

J Jiang, P Streli, X Luo, C Gebhardt, C Holz - European Conference on …, 2024 - Springer
Mixed Reality systems aim to estimate a user's full-body joint configurations from just the
pose of the end effectors, primarily head and hand poses. Existing methods often involve …