Journal article · 2026 · Open access
MvP: Learning Motion Prior for Diffusion-Based 3D Human Pose Estimation
IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–16 · Published 1 January 2026 · DOI 10.1109/tpami.2026.3751442
In brief
“MvP: Learning Motion Prior for Diffusion-Based 3D Human Pose Estimation” is a 2026 journal article by Bing Han and 5 co-authors, published in IEEE Transactions on Pattern Analysis and Machine Intelligence. OpenAlex counts 0 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Transactions on Pattern Analysis and Machine Intelligence.
- Citations
- 0
- Authors
- 6
Abstract
Recent diffusion-based solutions for 3D Human Pose Estimation (HPE) leverage generative modeling to address depth ambiguity and uncertainty in 2D-to-3D lifting. While substantial progress has been made in spatial accuracy, the generation of temporally coherent trajectories remains largely underexplored, which is crucial for understanding realistic human motion. In this work, we propose to model a motion prior for temporally consistent joint trajectories, together with a pose prior for anatomically plausible 3D poses, through independent diffusion models. Specifically, we represent motion using relative joint displacements, defined as the positional differences of joints between frames. The motion prior thus refers to the distribution of relative joint-displacement sequences modeled by the displacement denoiser. Motivated by the observation that human joint motion is typically smooth over short time periods, we introduce a keyframe denoiser to estimate poses at uniformly sampled keyframes, which also serve as anchors for displacement accumulation. Accordingly, we decompose 3D HPE into keyframe estimation and displacement estimation. Two specialized denois ers with exchanged attention orders and independent objec tives are designed to capture spatial correlations and temporal dependencies, respectively. We further introduce an endpoint corrected pose aggregation scheme that accumulates predicted displacements while maintaining consistency between adjacent keyframes. Extensive evaluations on three widely used 3D HPE benchmarks, Human3.6M (H36M), MPI-INF-3DHP (3DHP), and the challenging in-the-wild 3DPW, demonstrate the effectiveness of our method in balancing spatial accuracy and temporal smoothness. Notably, MvP achieves competitive spatial accuracy under zero-shot evaluation and improved temporal consistency after adaptation to the target domain.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Han, B., Zhuang, C., Zuo, Z., Gao, P., Qin, J., & Sebe, N. (2026). MvP: Learning Motion Prior for Diffusion-Based 3D Human Pose Estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–16. https://doi.org/10.1109/tpami.2026.3751442
MLA 9
Han, Bing, et al. “MvP: Learning Motion Prior for Diffusion-Based 3D Human Pose Estimation.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, 2026, pp. 1–16. https://doi.org/10.1109/tpami.2026.3751442.
Chicago
Han, Bing, Chenyi Zhuang, Zhi Zuo, Pan Gao, Jie Qin, and Nicu Sebe. 2026. “MvP: Learning Motion Prior for Diffusion-Based 3D Human Pose Estimation.” IEEE Transactions on Pattern Analysis and Machine Intelligence PP: 1–16. https://doi.org/10.1109/tpami.2026.3751442.
Harvard
Han, B. et al. (2026) ‘MvP: Learning Motion Prior for Diffusion-Based 3D Human Pose Estimation’, IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, pp. 1–16. doi:10.1109/tpami.2026.3751442.
IEEE
B. Han, C. Zhuang, Z. Zuo, P. Gao, J. Qin, and N. Sebe, “MvP: Learning Motion Prior for Diffusion-Based 3D Human Pose Estimation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, pp. 1–16, 2026, doi: 10.1109/tpami.2026.3751442.
BibTeX
@article{han2026learning,
title = {{MvP: Learning Motion Prior for Diffusion-Based 3D Human Pose Estimation}},
author = {Han, Bing and Zhuang, Chenyi and Zuo, Zhi and Gao, Pan and Qin, Jie and Sebe, Nicu},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {PP},
pages = {1--16},
doi = {10.1109/tpami.2026.3751442},
url = {https://doi.org/10.1109/tpami.2026.3751442}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- 3D human pose estimation
- diffusion models
- motion priors
- displacement estimation
- temporal coherence
- 2D-to-3D lifting
- zero-shot generalization
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Han, B., Zhuang, C., Zuo, Z., Gao, P., Qin, J., & Sebe, N. (2026). MvP: Learning Motion Prior for Diffusion-Based 3D Human Pose Estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–16. https://doi.org/10.1109/tpami.2026.3751442
How many times has this paper been cited?
0 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at IEEE Transactions on Pattern Analysis and Machine Intelligence: sign in and open the full text from this page.
Who wrote this paper?
Bing Han, Chenyi Zhuang, Zhi Zuo, Pan Gao, Jie Qin, Nicu Sebe.
What is the DOI of this paper?
10.1109/tpami.2026.3751442, permanently at https://doi.org/10.1109/tpami.2026.3751442. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.