Skip to search formSkip to main contentSkip to account menu
DOI:10.1109/RO-MAN57019.2023.10309317 - Corpus ID: 258048451
@article{Yin2023ControllableMS, title={Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models}, author={Wenjie Yin and Ruibo Tu and Hang Yin and Danica Kragic and Hedvig Kjellstr{\"o}m and M{\aa}rten Bj{\"o}rkman}, journal={2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)}, year={2023}, pages={1102-1108}, url={https://api.semanticscholar.org/CorpusID:258048451}}
- Wenjie Yin, Ruibo Tu, Mårten Björkman
- Published in IEEE International Symposium… 3 April 2023
- Computer Science, Engineering
MoDiff, an autoregressive probabilistic diffusion model over motion sequences conditioned on control contexts of other modalities, is introduced and the benefits of diffusion data dropout for robust synthesis and reconstruction of high-fidelity motion close to recorded data are shown.
1 Citation
1
Figures and Tables from this paper
- figure 1
- figure 2
- figure 3
- figure 4
- figure 5
- figure 6
- table I
- table II
Topics
Motion Sequences (opens in a new tab)Human Motion Synthesis (opens in a new tab)Autoregressive Diffusion Models (opens in a new tab)
Ask This Paper
BETA
AI-Powered
Ask This Paper
BETA
AI-Powered
Unknown Error
An unexpected error occurred. Please try again.
No Answer Found
Ask another question that can be answered by this paper or rephrase your question.
We are still processing this paper
Please try again later.
Question Answering Unavailable
Please try again later.
No Response
The server took too long to answer your question. You can either rephrase your question or wait until it is less busy.
AI-Generated
Thank you for your feedback!
We're sorry, something went wrong while submitting this feedback.
Thank you for your feedback!
We're sorry, something went wrong while submitting this feedback.
Supporting Statements
Our system tries to constrain to information found in this paper. Results quality may vary. Learn more about how we generate these answers.
Feedback?
One Citation
- Wenjie YinYi YuHang YinDanica KragicMårten Björkman
- 2024
Computer Science
AAAI
This work constructs the bias from the source domain keyframes and applies them as the gradient of content constraints, yielding a framework with keyframe manifold constraint gradients (KMCGs) and performs a human study for a subjective assessment of the quality of generated dance motions.
28 References
- Wenjie YinHang YinD. KragicMårten Björkman
- 2021
Computer Science
2021 30th IEEE International Conference on Robot…
A probabilistic generative model is proposed to synthesize and reconstruct long horizon motion sequences conditioned on past information and control signals, such as the path along which an individual is moving, to reconstructing missing markers and achieving comparable results on generating realistic future poses.
- 8
- Highly Influential[PDF]
- I. HabibieDaniel HoldenJonathan SchwarzJ. YearsleyT. Komura
- 2017
Computer Science
BMVC
A novel generative model of human motion that can be trained using a large motion capture dataset, and allows users to produce animations from high-level control signals that can predict the movements of the human body over long horizons more accurately than state-of-the-art methods.
- 138
- PDF
- Zhiyong WangJinxiang ChaiShi-hong Xia
- 2021
Computer Science, Engineering
IEEE Transactions on Visualization and Computer…
A new generative deep learning network for human motion synthesis and control that is compact, contact-aware, and can generate an infinite number of naturally looking motions with infinite lengths is introduced.
- 60 [PDF]
- Guy TevetSigal RaabBrian GordonYonatan ShafirDaniel Cohen-OrAmit H. Bermano
- 2023
Computer Science
ICLR
Motion Diffusion Model (MDM), a carefully adapted classifier-free diffusion-based generative model for the human motion domain, is introduced, a transformer-based approach, enabling different modes of conditioning, and different generation tasks.
- 341 [PDF]
- Simon AlexandersonRajmund NagyJ. BeskowG. Henter
- 2023
Computer Science
ACM Trans. Graph.
This work adapts the DiffWave architecture to model 3D pose sequences, putting Conformers in place of dilated convolutions for improved modelling power and demonstrates control over motion style, using classifier-free guidance to adjust the strength of the stylistic expression.
- 60 [PDF]
- Julieta MartinezMichael J. BlackJ. Romero
- 2017
Computer Science
2017 IEEE Conference on Computer Vision and…
It is shown that, surprisingly, state of the art performance can be achieved by a simple baseline that does not attempt to model motion at all, and a simple and scalable RNN architecture is proposed that obtains state-of-the-art performance on human motion prediction.
- 793 [PDF]
- Germán BarqueroSergio EscaleraCristina Palmero
- 2023
Computer Science
2023 IEEE/CVF International Conference on…
BeLFusion is a model that, for the first time, leverages latent diffusion models in HMP to sample from a behavioral latent space where behavior is disentangled from pose and motion, and its predictions display a variety of behaviors that are significantly more realistic, and coherent with past motion than the state of the art.
- 25 [PDF]
- Yi ZhouZimo LiShuangjiu XiaoC. HeZeng HuangHao Li
- 2018
Computer Science
ICLR
This work is the first to the knowledge that demonstrates the ability to generate over 18,000 continuous frames (300 seconds) of new complex human motion w.r.t. different styles.
- 202
- PDF
- Mingyuan ZhangZhongang Cai Ziwei Liu
- 2024
Computer Science
IEEE transactions on pattern analysis and machine…
The proposed MotionDiffuse is one of the first diffusion model-based text-driven motion generation frameworks, which demonstrates several desired properties over existing methods, and outperforms existing SoTA methods by convincing margins on text-driven motion generation and action-conditioned motion generation.
- 239 [PDF]
- Judith BütepageMichael J. BlackD. KragicH. Kjellström
- 2017
Computer Science
2017 IEEE Conference on Computer Vision and…
The results show that deep feedforward networks, trained from a generic mocap database, can successfully be used for feature extraction from human motion data and that this representation can be used as a foundation for classification and prediction.
- 383 [PDF]
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers