FMPose3D: monocular 3D pose estimation via flow matching

• URL: http://arxiv.org/abs/2602.05755v1
• Date: Thu, 05 Feb 2026 15:25:35 GMT
• Title: FMPose3D: monocular 3D pose estimation via flow matching
• Authors: Ti Wang, Xiaohang Yu, Mackenzie Weygandt Mathis,
• Abstract summary: We use Flow Matching to learn a velocity field defined by an Ordinary Differential Equation (ODE)<n>We propose a novel generative pose estimation framework, FMPose3D, that formulates 3D pose estimation as a conditional distribution transport problem.<n>FMPose3D surpasses existing methods on the widely used human pose estimation benchmarks Human3.6M and MPI-INF-3DHP, and further achieves state-of-the-art performance on the 3D animal pose datasets Animal3D and CtrlAni3D.
• Score: 3.599033387924161
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Monocular 3D pose estimation is fundamentally ill-posed due to depth ambiguity and occlusions, thereby motivating probabilistic methods that generate multiple plausible 3D pose hypotheses. In particular, diffusion-based models have recently demonstrated strong performance, but their iterative denoising process typically requires many timesteps for each prediction, making inference computationally expensive. In contrast, we leverage Flow Matching (FM) to learn a velocity field defined by an Ordinary Differential Equation (ODE), enabling efficient generation of 3D pose samples with only a few integration steps. We propose a novel generative pose estimation framework, FMPose3D, that formulates 3D pose estimation as a conditional distribution transport problem. It continuously transports samples from a standard Gaussian prior to the distribution of plausible 3D poses conditioned only on 2D inputs. Although ODE trajectories are deterministic, FMPose3D naturally generates various pose hypotheses by sampling different noise seeds. To obtain a single accurate prediction from those hypotheses, we further introduce a Reprojection-based Posterior Expectation Aggregation (RPEA) module, which approximates the Bayesian posterior expectation over 3D hypotheses. FMPose3D surpasses existing methods on the widely used human pose estimation benchmarks Human3.6M and MPI-INF-3DHP, and further achieves state-of-the-art performance on the 3D animal pose datasets Animal3D and CtrlAni3D, demonstrating strong performance across both 3D pose domains. The code is available at https://github.com/AdaptiveMotorControlLab/FMPose3D.

Related papers

• Flow Matching for Probabilistic Monocular 3D Human Pose Estimation [12.773184391232467]
  We propose FMPose, a probabilistic 3D human pose estimation method based on the flow matching generative approach.<n>The FMPose learns the optimal transport from a simple source distribution to the plausible 3D human pose distribution via continuous normalizing flows.<n>Compared to diffusion-based methods, the FMPose with optimal transport produces faster and more accurate 3D pose generations.
  arXiv  Detail & Related papers  (2026-01-23T14:09:33Z)
• DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models [67.50989119438508]
  We introduce DSplats, a novel method that directly denoises multiview images using Gaussian-based Reconstructors to produce realistic 3D assets.<n>Our experiments demonstrate that DSplats not only produces high-quality, spatially consistent outputs, but also sets a new standard in single-image to 3D reconstruction.
  arXiv  Detail & Related papers  (2024-12-11T07:32:17Z)
• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
  PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices.<n>Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-29T15:28:15Z)
• UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues [55.69339788566899]
  UPose3D is a novel approach for multi-view 3D human pose estimation. It improves robustness and flexibility without requiring direct 3D annotations.
  arXiv  Detail & Related papers  (2024-04-23T00:18:00Z)
• Diffusion-based Pose Refinement and Muti-hypothesis Generation for 3D Human Pose Estimaiton [27.708016152889787]
  Previous probabilistic models for 3D Human Pose Estimation (3DHPE) aimed to enhance pose accuracy by generating multiple hypotheses. Most of the hypotheses generated deviate substantially from the true pose. Compared to deterministic models, the excessive uncertainty in probabilistic models leads to weaker performance in single-hypothesis prediction. We propose a diffusion-based refinement framework called DRPose, which refines the output of deterministic models by reverse diffusion.
  arXiv  Detail & Related papers  (2024-01-10T04:07:50Z)
• D3PRefiner: A Diffusion-based Denoise Method for 3D Human Pose Refinement [3.514184876338779]
  A Diffusion-based 3D Pose Refiner is proposed to refine the output of any existing 3D pose estimator. We leverage the architecture of current diffusion models to convert the distribution of noisy 3D poses into ground truth 3D poses. Experimental results demonstrate the proposed architecture can significantly improve the performance of current sequence-to-sequence 3D pose estimators.
  arXiv  Detail & Related papers  (2024-01-08T14:21:02Z)
• ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation [71.2556016049579]
  ManiPose is a manifold-constrained multi-hypothesis model for human-pose 2D-to-3D lifting.<n>By constraining the outputs to lie on the human pose manifold, ManiPose guarantees the consistency of all hypothetical poses.<n>We showcase the performance of ManiPose on real-world datasets, where it outperforms state-of-the-art models in pose consistency.
  arXiv  Detail & Related papers  (2023-12-11T13:50:10Z)
• Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation [64.874000550443]
  A Diffusion-based 3D Pose estimation (D3DP) method with Joint-wise reProjection-based Multi-hypothesis Aggregation (JPMA) is proposed. The proposed JPMA assembles multiple hypotheses generated by D3DP into a single 3D pose for practical use. Our method outperforms the state-of-the-art deterministic and probabilistic approaches by 1.5% and 8.9%, respectively.
  arXiv  Detail & Related papers  (2023-03-21T04:00:47Z)
• A generic diffusion-based approach for 3D human pose prediction in the wild [68.00961210467479]
  3D human pose forecasting, i.e., predicting a sequence of future human 3D poses given a sequence of past observed ones, is a challenging-temporal task. We provide a unified formulation in which incomplete elements (no matter in the prediction or observation) are treated as noise and propose a conditional diffusion model that denoises them and forecasts plausible poses. We investigate our findings on four standard datasets and obtain significant improvements over the state-of-the-art.
  arXiv  Detail & Related papers  (2022-10-11T17:59:54Z)
• Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows [24.0966076588569]
  We propose a normalizing flow based method that exploits the deterministic 3D-to-2D mapping to solve the ambiguous inverse 2D-to-3D problem. We evaluate our approach on the two benchmark datasets Human3.6M and MPI-INF-3DHP, outperforming all comparable methods in most metrics.
  arXiv  Detail & Related papers  (2021-07-29T07:33:14Z)
• Weakly Supervised Generative Network for Multiple 3D Human Pose Hypotheses [74.48263583706712]
  3D human pose estimation from a single image is an inverse problem due to the inherent ambiguity of the missing depth. We propose a weakly supervised deep generative network to address the inverse problem.
  arXiv  Detail & Related papers  (2020-08-13T09:26:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.