liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Flow Matching for Probabilistic Monocular 3D Human Pose Estimation
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-8509-4952
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-6091-861X
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-0675-2794
2026 (English)In: Transactions on Machine Learning Research, E-ISSN 2835-8856Article in journal (Refereed) Accepted
Abstract [en]

Recovering 3D human poses from a monocular camera view is a highly ill-posed problem due to the depth ambiguity. Earlier studies on 3D human pose lifting from 2D often contain incorrect-yet-overconfident 3D estimations. To mitigate the problem, emerging probabilistic approaches treat the 3D estimations as a distribution, taking into account the uncertainty measurement of the poses. Falling in a similar category, we proposed FMPose, a probabilistic 3D human pose estimation method based on the flow matching generative approach. Conditioned on the 2D cues, the flow matching scheme learns the optimal transport from a simple source distribution to the plausible 3D human pose distribution via continuous normalizing flows. The 2D lifting condition is modeled via graph convolutional networks, leveraging the learnable connections between human body joints as the graph structure for feature aggregation. While trade-offs between processing time and precision exist, already in the equal-accuracy comparison, FMPose exhibits significantly faster processing time than the diffusion model, and also offers another faster and more accurate configuration. Experimental results show major improvements of our FMPose over current state-of-the-art methods on two common benchmarks for 3D human pose estimation, namely Human3.6M, MPI-INF-3DHP. Additionally, FMPose shows competitive performance on the more challenging 3DPW dataset. The code implementation is available at https://github.com/cuongle1206/FMPose.

Place, publisher, year, edition, pages
2026.
National Category
Computer and Information Sciences Computer Vision and Learning Systems
Identifiers
URN: urn:nbn:se:liu:diva-228870OAI: oai:DiVA.org:liu-228870DiVA, id: diva2:2112978
Available from: 2026-10-27 Created: 2026-10-27 Last updated: 2026-11-05

Open Access in DiVA

fulltext(13237 kB)50 downloads
File information
File name FULLTEXT01.pdfFile size 13237 kBChecksum SHA-512
df519e5cd5df077b3dc382cda15abf3dc2de509d74aa338463945a0b05ce04270640891093986e5e0697c98742a780af1b80b19723585e58b90ddb57c9a42a0a
Type fulltextMimetype application/pdf

Other links

Förlagets fulltext/Publisher's full text

Authority records

Le, CuongMelnyk, PavloWandt, BastianWadenbäck, Mårten

Search in DiVA

By author/editor
Le, CuongMelnyk, PavloWandt, BastianWadenbäck, Mårten
By organisation
Computer VisionFaculty of Science & Engineering
In the same journal
Transactions on Machine Learning Research
Computer and Information SciencesComputer Vision and Learning Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 50 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 632 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf