Publications (11)
From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humans
Marilyn Keller, Keenon Werling, Soyong Shin +4
Great progress has been made in estimating 3D human pose and shape from images and video by training neural networks to directly regress the parameters of parametric human models l…
ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information
Madalina Fiterau, Suvrat Bhooshan, Jason Fries +5
In healthcare applications, temporal variables that encode movement, health status and longitudinal patient evolution are often accompanied by rich structured information such as d…
Repurposing 2D Diffusion Models with Gaussian Atlas for 3D Generation
Tiange Xiang, Kai Li, Chengjiang Long +5
Recent advances in text-to-image diffusion models have been driven by the increasing availability of paired 2D data. However, the development of 3D diffusion models has been hinder…
Medical device surveillance with electronic health records
Alison Callahan, Jason A Fries, Christopher Ré +4
Post-market medical device surveillance is a challenge facing manufacturers, regulatory agencies, and health care providers. Electronic health records are valuable sources of real…
HumanScore: Benchmarking Human Motions in Generated Videos
Yusu Fang, Tiange Xiang, Tian Tan +4
Recent advances in model architectures, compute, and data scale have driven rapid progress in video generation, producing increasingly realistic content. Yet, no prior method syste…
AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale
Keenon Werling, Janelle Kaneda, Alan Tan +15
While reconstructing human poses in 3D from inexpensive sensors has advanced significantly in recent years, quantifying the dynamics of human motion, including the muscle-generated…
Artificial Intelligence for Prosthetics - challenge solutions
Åukasz KidziÅski, Carmichael Ong, Sharada Prasanna Mohanty +47
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a giv…
OccFusion: Rendering Occluded Humans with Generative Diffusion Priors
Adam Sun, Tiange Xiang, Scott Delp +2
Most existing human rendering methods require every part of the human to be fully visible throughout the input video. However, this assumption does not hold in real-life settings w…
Wild2Avatar: Rendering Humans Behind Occlusions
Tiange Xiang, Adam Sun, Scott Delp +3
Rendering the visual appearance of moving humans from occluded monocular videos is a challenging task. Most existing research renders 3D humans under ideal conditions, requiring a…
Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments
Åukasz KidziÅski, Sharada Prasanna Mohanty, Carmichael Ong +26
In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle c…
DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion
Tom Van Wouwe, Seunghwan Lee, Antoine Falisse +2
Motion capture from a limited number of body-worn sensors, such as inertial measurement units (IMUs) and pressure insoles, has important applications in health, human performance,…