Computer Science > Computer Vision and Pattern Recognition
arXiv:2404.19759 (cs)
[Submitted on 30 Apr 2024 (v1), last revised 30 Dec 2024 (this version, v3)]
Title:MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model
View a PDF of the paper titled MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model, by Wenxun Dai and 5 other authors
View PDFHTML (experimental)Abstract:This work introduces MotionLCM, extending controllable motion generation to a real-time level. Existing methods for spatial-temporal control in text-conditioned motion generation suffer from significant runtime inefficiency. To address this issue, we first propose the motion latent consistency model (MotionLCM) for motion generation, building on the motion latent diffusion model. By adopting one-step (or few-step) inference, we further improve the runtime efficiency of the motion latent diffusion model for motion generation. To ensure effective controllability, we incorporate a motion ControlNet within the latent space of MotionLCM and enable explicit control signals (i.e., initial motions) in the vanilla motion space to further provide supervision for the training process. By employing these techniques, our approach can generate human motions with text and control signals in real-time. Experimental results demonstrate the remarkable generation and controlling capabilities of MotionLCM while maintaining real-time runtime efficiency.
| Comments: | MotionLCM project version 1.0 (ECCV 2024) |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2404.19759 [cs.CV] |
| (orarXiv:2404.19759v3 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2404.19759 arXiv-issued DOI via DataCite |
Submission history
From: Wenxun Dai [view email][v1] Tue, 30 Apr 2024 17:59:47 UTC (928 KB)
[v2] Tue, 15 Oct 2024 14:22:49 UTC (1,808 KB)
[v3] Mon, 30 Dec 2024 08:43:06 UTC (1,809 KB)
Full-text links:
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
- Other Formats
View a PDF of the paper titled MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model, by Wenxun Dai and 5 other authors
References & Citations
Bookmark
Bibliographic and Citation Tools
Bibliographic Explorer(What is the Explorer?)
Connected Papers(What is Connected Papers?)
Litmaps(What is Litmaps?)
scite Smart Citations(What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv(What is alphaXiv?)
CatalyzeX Code Finder for Papers(What is CatalyzeX?)
DagsHub(What is DagsHub?)
Gotit.pub(What is GotitPub?)
Hugging Face(What is Huggingface?)
Papers with Code(What is Papers with Code?)
ScienceCast(What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower(What are Influence Flowers?)
CORE Recommender(What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community?Learn more about arXivLabs.