Physdiff: Physics-guided human motion diffusion model

Y Yuan, J Song, U Iqbal, A Vahdat… - Proceedings of the …, 2023 - openaccess.thecvf.com
Denoising diffusion models hold great promise for generating diverse and realistic human
motions. However, existing motion diffusion models largely disregard the laws of physics in …

Ai choreographer: Music conditioned 3d dance generation with aist++

R Li, S Yang, DA Ross… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
We present AIST++, a new multi-modal dataset of 3D dance motion and music, along with
FACT, a Full-Attention Cross-modal Transformer network for generating 3D dance motion …

Human motion diffusion as a generative prior

Y Shafir, G Tevet, R Kapon, AH Bermano - arXiv preprint arXiv:2303.01418, 2023 - arxiv.org
Recent work has demonstrated the significant potential of denoising diffusion models for
generating human motion, including text-to-motion capabilities. However, these methods are …

Long-term human motion prediction with scene context

Z Cao, H Gao, K Mangalam, QZ Cai, M Vo… - Computer Vision–ECCV …, 2020 - Springer
Human movement is goal-directed and influenced by the spatial layout of the objects in the
scene. To plan future human motion, it is crucial to perceive the environment–imagine how …

Character controllers using motion vaes

HY Ling, F Zinno, G Cheng… - ACM Transactions on …, 2020 - dl.acm.org
A fundamental problem in computer animation is that of realizing purposeful and realistic
human movement given a sufficiently-rich set of motion capture clips. We learn data-driven …

Stochastic scene-aware motion prediction

M Hassan, D Ceylan, R Villegas… - Proceedings of the …, 2021 - openaccess.thecvf.com
A long-standing goal in computer vision is to capture, model, and realistically synthesize
human behavior. Specifically, by learning from data, our goal is to enable virtual humans to …

Learning 3d human dynamics from video

A Kanazawa, JY Zhang, P Felsen… - Proceedings of the …, 2019 - openaccess.thecvf.com
From an image of a person in action, we can easily guess the 3D motion of the person in the
immediate past and future. This is because we have a mental model of 3D human dynamics …

Hierarchical generation of human-object interactions with diffusion probabilistic models

H Pi, S Peng, M Yang, X Zhou… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
This paper presents a novel approach to generating the 3D motion of a human interacting
with a target object, with a focus on solving the challenge of synthesizing long-range and …

Probabilistic transformer for time series analysis

B Tang, DS Matteson - Advances in Neural Information …, 2021 - proceedings.neurips.cc
Generative modeling of multivariate time series has remained challenging partly due to the
complex, non-deterministic dynamics across long-distance timesteps. In this paper, we …

Synthesis of compositional animations from textual descriptions

A Ghosh, N Cheema, C Oguz… - Proceedings of the …, 2021 - openaccess.thecvf.com
How can we animate 3D-characters from a movie script or move robots by simply telling
them what we would like them to do?" How unstructured and complex can we make a …