Deterministic-to-Stochastic Diverse Latent Feature Mapping for Human Motion Synthesis

• URL: http://arxiv.org/abs/2505.00998v1
• Date: Fri, 02 May 2025 04:48:28 GMT
• Title: Deterministic-to-Stochastic Diverse Latent Feature Mapping for Human Motion Synthesis
• Authors: Yu Hua, Weiming Liu, Gui Xu, Yaqing Hou, Yew-Soon Ong, Qiang Zhang,
• Abstract summary: Human motion synthesis aims to generate plausible human motion sequences.<n>Recent score-based generative models (SGMs) have demonstrated impressive results on this task.<n>We propose a Deterministic-to-Stochastic Diverse Latent Feature Mapping (DSDFM) method for human motion synthesis.
• Score: 31.082402451716973
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human motion synthesis aims to generate plausible human motion sequences, which has raised widespread attention in computer animation. Recent score-based generative models (SGMs) have demonstrated impressive results on this task. However, their training process involves complex curvature trajectories, leading to unstable training process. In this paper, we propose a Deterministic-to-Stochastic Diverse Latent Feature Mapping (DSDFM) method for human motion synthesis. DSDFM consists of two stages. The first human motion reconstruction stage aims to learn the latent space distribution of human motions. The second diverse motion generation stage aims to build connections between the Gaussian distribution and the latent space distribution of human motions, thereby enhancing the diversity and accuracy of the generated human motions. This stage is achieved by the designed deterministic feature mapping procedure with DerODE and stochastic diverse output generation procedure with DivSDE.DSDFM is easy to train compared to previous SGMs-based methods and can enhance diversity without introducing additional training parameters.Through qualitative and quantitative experiments, DSDFM achieves state-of-the-art results surpassing the latest methods, validating its superiority in human motion synthesis.

Related papers

• A Plug-and-Play Multi-Criteria Guidance for Diverse In-Betweening Human Motion Generation [22.473976066685594]
  In this paper, we propose a novel method, termed the Multi-Criteria Guidance with In-Betweening Motion Model (MCG-IMM)<n>A key strength of MCG-IMM lies in its plug-and-play nature: it enhances the diversity of motions generated by pretrained models without introducing additional parameters.<n>Experiments on four popular human motion datasets demonstrate that MCG-IMM consistently state-of-the-art methods in in-betweening motion generation task.
  arXiv  Detail & Related papers  (2025-08-03T05:06:37Z)
• A Spatio-temporal Continuous Network for Stochastic 3D Human Motion Prediction [15.033378809142299]
  We propose a novel method called STC, for continuous human motion prediction, which consists of two stages.<n>In the first stage, we propose atemporal continuous network to generate smoother human motion sequences.<n>In the second stage, STCN endeavors to acquire the Gaussian mixture distribution (GMM) of observed motion sequences.
  arXiv  Detail & Related papers  (2025-08-03T04:53:39Z)
• GENMO: A GENeralist Model for Human MOtion [64.16188966024542]
  We present GENMO, a unified Generalist Model for Human Motion that bridges motion estimation and generation in a single framework.<n>Our key insight is to reformulate motion estimation as constrained motion generation, where the output motion must precisely satisfy observed conditioning signals.<n>Our novel architecture handles variable-length motions and mixed multimodal conditions (text, audio, video) at different time intervals, offering flexible control.
  arXiv  Detail & Related papers  (2025-05-02T17:59:55Z)
• Multi-Scale Incremental Modeling for Enhanced Human Motion Prediction in Human-Robot Collaboration [0.0]
  This paper presents a novel framework that explicitly encodes incremental models across multiple-temporal scales.<n>Experiments on four datasets demonstrate substantial improvements in continuity, biomechanical consistency, and long-term forecast stability.<n>The proposed multi-scale incremental approach provides a powerful technique for advancing human motion prediction capabilities critical for seamless human-robot interaction.
  arXiv  Detail & Related papers  (2024-12-16T10:20:46Z)
• MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints [50.61346764110482]
  We integrate a musculoskeletal system with a learnable parametric hand model, MANO, to create MS-MANO. This model emulates the dynamics of muscles and tendons to drive the skeletal system, imposing physiologically realistic constraints on the resulting torque trajectories. We also propose a simulation-in-the-loop pose refinement framework, BioPR, that refines the initial estimated pose through a multi-layer perceptron network.
  arXiv  Detail & Related papers  (2024-04-16T02:18:18Z)
• Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
  Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
  arXiv  Detail & Related papers  (2024-02-19T15:57:39Z)
• Persistent-Transient Duality: A Multi-mechanism Approach for Modeling Human-Object Interaction [58.67761673662716]
  Humans are highly adaptable, swiftly switching between different modes to handle different tasks, situations and contexts. In Human-object interaction (HOI) activities, these modes can be attributed to two mechanisms: (1) the large-scale consistent plan for the whole activity and (2) the small-scale children interactive actions that start and end along the timeline. This work proposes to model two concurrent mechanisms that jointly control human motion.
  arXiv  Detail & Related papers  (2023-07-24T12:21:33Z)
• Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognition [32.07659338674024]
  We introduce a novel data augmentation method for skeleton-based action recognition tasks. Our method outperforms the state-of-the-art (SOTA) motion generation approaches on different naturality and diversity metrics.
  arXiv  Detail & Related papers  (2023-02-26T23:02:33Z)
• Executing your Commands via Motion Diffusion in Latent Space [51.64652463205012]
  We propose a Motion Latent-based Diffusion model (MLD) to produce vivid motion sequences conforming to the given conditional inputs. Our MLD achieves significant improvements over the state-of-the-art methods among extensive human motion generation tasks.
  arXiv  Detail & Related papers  (2022-12-08T03:07:00Z)
• Skeleton2Humanoid: Animating Simulated Characters for Physically-plausible Motion In-betweening [59.88594294676711]
  Modern deep learning based motion synthesis approaches barely consider the physical plausibility of synthesized motions. We propose a system Skeleton2Humanoid'' which performs physics-oriented motion correction at test time. Experiments on the challenging LaFAN1 dataset show our system can outperform prior methods significantly in terms of both physical plausibility and accuracy.
  arXiv  Detail & Related papers  (2022-10-09T16:15:34Z)

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.