Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos

• URL: http://arxiv.org/abs/2605.26879v1
• Date: Tue, 26 May 2026 11:38:36 GMT
• Title: Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos
• Abstract summary: We introduce HTD-Refine, a post-processing framework that augments Human Motion Recovery (HMR) pipelines using explicitly estimated high-order temporal dynamics.<n>At the core of our system is PVA-Net, a temporal transformer that infers per-joint 2D positions, 3D velocities, and 3D accelerations directly from a monocular video.
• Score: 65.51845732149306
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Human motion recovered from monocular videos often appears overly smooth or dynamically inconsistent, even when joint positions are numerically accurate. We observe that this limitation stems from the absence of reliable high-order temporal cues -- velocity and acceleration -- which are essential for reconstructing motion that exhibits realistic momentum, timing, and high-frequency detail. We introduce HTD-Refine, a post-processing framework that augments existing Human Motion Recovery (HMR) pipelines using explicitly estimated high-order temporal dynamics. At the core of our system is PVA-Net, a temporal transformer that infers per-joint 2D positions, 3D velocities, and 3D accelerations directly from a monocular video. These predicted dynamics serve as soft yet informative constraints in a global optimization procedure that refines world-space trajectories, significantly reducing jitter, suppressing over-smoothing, and restoring physically plausible motion. Extensive experiments on challenging in-the-wild benchmarks show that HTD-Refine consistently improves state-of-the-art HMR methods, yielding more accurate global trajectories and substantially more natural motion dynamics. Our results highlight the critical role of high-order temporal modeling in advancing monocular human motion recovery.

Related papers

• MotionMAR: Multi-scale Auto-Regressive Human Motion Reconstruction from Sparse Observations [51.837372131319285]
  MotionMAR is a framework for motion reconstruction from sparse observations.<n>It first estimates the global trajectory of human motion and then gradually refines the temporal details.<n>MotionMAR achieves state-of-the-art accuracy on the AMASS dataset.
  arXiv  Detail & Related papers  (2026-06-22T08:15:56Z)
• RiGS: Rigid-aware 4D Gaussian Splatting from a Single Monocular Video [38.8840959968641]
  We present Rigid-aware 4D Gaussian Splatting (RiGS), which simultaneously captures motions across multiple temporal scales.<n>RiGS achieves state-of-the-art performance on novel view synthesis benchmarks.
  arXiv  Detail & Related papers  (2026-05-22T14:20:39Z)
• Bézier Degradation Modeling for LiDAR-based Human Motion Capture [21.718401755735773]
  BMLiCap is a coarse-to-fine framework that models motion using temporally compressible Bézier curves.<n>It achieves state-of-the-art accuracy and temporal continuity in complex scenes.
  arXiv  Detail & Related papers  (2026-05-19T09:56:52Z)
• PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation [75.96085587438279]
  Existing video rewards primarily rely on 2D perceptual signals, without explicitly modeling the 3D body state, contact, and dynamics underlying articulated human motion.<n>We propose PhyMotion, a structured, fine-grained motion reward that grounds recovered 3D human trajectories in a physics simulator and evaluates motion quality along multiple dimensions of physical feasibility.<n>Experiments show that PhyMotion achieves stronger correlation with human judgments than existing reward formulations.
  arXiv  Detail & Related papers  (2026-05-14T02:12:13Z)
• Mango-GS: Enhancing Spatio-Temporal Consistency in Dynamic Scenes Reconstruction using Multi-Frame Node-Guided 4D Gaussian Splatting [17.957935001501106]
  We present Mango-GS, a node-guided framework for high-fidelity 4D reconstruction.<n>We leverage a temporal Transformer to model motion dependencies within a short window of frames.<n>Mango-GS achieves state-of-the-art reconstruction quality and real-time rendering speed.
  arXiv  Detail & Related papers  (2026-03-12T05:00:16Z)
• PEGS: Physics-Event Enhanced Large Spatiotemporal Motion Reconstruction via 3D Gaussian Splatting [8.672740691555736]
  PEGS is a framework that integrates Physical priors with Event stream enhancement within a 3D Gaussian Splatting pipeline.<n>We introduce a triple-level supervision scheme that enforces physical plausibility via an acceleration constraint.<n>We also contribute the first RGB-Event paired targeting the natural, fast rigid motion across diverse datasets.
  arXiv  Detail & Related papers  (2025-11-21T10:27:51Z)
• Geometric Neural Distance Fields for Learning Human Motion Priors [51.99890740169883]
  We introduce a novel 3D generative human motion prior that enables robust, temporally consistent, and physically plausible 3D motion recovery.<n>Our experiments show significant and consistent gains: trained on the AMASS dataset, NRMF remarkably generalizes across multiple input modalities.
  arXiv  Detail & Related papers  (2025-09-11T17:58:18Z)
• Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera [49.82535393220003]
  Dyn-HaMR is the first approach to reconstruct 4D global hand motion from monocular videos recorded by dynamic cameras in the wild.<n>We show that our approach significantly outperforms state-of-the-art methods in terms of 4D global mesh recovery.<n>This establishes a new benchmark for hand motion reconstruction from monocular video with moving cameras.
  arXiv  Detail & Related papers  (2024-12-17T12:43:10Z)
• Temporal-Aware Refinement for Video-based Human Pose and Shape Recovery [20.566505924677013]
  We propose a temporal-aware refining network (TAR) to explore temporal-aware global and local image features for accurate pose and shape recovery. Our TAR obtains more accurate results than previous state-of-the-art methods on popular benchmarks, i.e., 3DPW, MPI-INF-3DHP, and Human3.6M.
  arXiv  Detail & Related papers  (2023-11-16T03:35:17Z)
• GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras [99.07219478953982]
  We present an approach for 3D global human mesh recovery from monocular videos recorded with dynamic cameras. We first propose a deep generative motion infiller, which autoregressively infills the body motions of occluded humans based on visible motions. In contrast to prior work, our approach reconstructs human meshes in consistent global coordinates even with dynamic cameras.
  arXiv  Detail & Related papers  (2021-12-02T18:59:54Z)

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.