AStF: Motion Style Transfer via Adaptive Statistics Fusor

• URL: http://arxiv.org/abs/2511.04192v1
• Date: Thu, 06 Nov 2025 08:51:24 GMT
• Title: AStF: Motion Style Transfer via Adaptive Statistics Fusor
• Authors: Hanmo Chen, Chenghao Xu, Jiexi Yan, Cheng Deng,
• Abstract summary: We propose a novel Adaptive Statistics Fusor (AStF) which consists of Style Distemporalment Module (SDM) and High-Order Multi-Statistics Attention (HO-SAttn)<n> Experimental results show that, by providing a more comprehensive model, our proposed AStF shows proficiency in motion style over state-of-the-arts techniques.
• Score: 58.660938790014455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human motion style transfer allows characters to appear less rigidity and more realism with specific style. Traditional arbitrary image style transfer typically process mean and variance which is proved effective. Meanwhile, similar methods have been adapted for motion style transfer. However, due to the fundamental differences between images and motion, relying on mean and variance is insufficient to fully capture the complex dynamic patterns and spatiotemporal coherence properties of motion data. Building upon this, our key insight is to bring two more coefficient, skewness and kurtosis, into the analysis of motion style. Specifically, we propose a novel Adaptive Statistics Fusor (AStF) which consists of Style Disentanglement Module (SDM) and High-Order Multi-Statistics Attention (HOS-Attn). We trained our AStF in conjunction with a Motion Consistency Regularization (MCR) discriminator. Experimental results show that, by providing a more comprehensive model of the spatiotemporal statistical patterns inherent in dynamic styles, our proposed AStF shows proficiency superiority in motion style transfers over state-of-the-arts. Our code and model are available at https://github.com/CHMimilanlan/AStF.

Related papers

• MOTIF: Learning Action Motifs for Few-shot Cross-Embodiment Transfer [55.982504915794514]
  Cross-embodiment policies typically rely on shared-private architectures.<n>We introduce MOTIF for efficient few-shot cross-embodiment transfer.<n>We show that MOTIF significantly outperforms strong baselines in few-shot transfer scenarios.
  arXiv  Detail & Related papers  (2026-02-14T13:21:40Z)
• FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation [51.110607281391154]
  FlowMo is a training-free guidance method for enhancing motion coherence in text-to-video models.<n>It estimates motion coherence by measuring the patch-wise variance across the temporal dimension and guides the model to reduce this variance dynamically during sampling.
  arXiv  Detail & Related papers  (2025-06-01T19:55:33Z)
• Dance Like a Chicken: Low-Rank Stylization for Human Motion Diffusion [28.94750481325469]
  We introduce LoRA-MDM, a framework for motion stylization that generalizes to complex actions while maintaining editability.<n>Our key insight is that adapting the generative prior to include the style, while preserving its overall distribution, is more effective than modifying each individual motion during generation.<n>LoRA-MDM learns to adapt the prior to include the reference style using only a few samples.
  arXiv  Detail & Related papers  (2025-03-25T11:23:34Z)
• SMCD: High Realism Motion Style Transfer via Mamba-based Diffusion [12.426879081036116]
  Motion style transfer enables virtual digital humans to rapidly switch between different styles of the same motion.<n>Most existing methods adopt a two-stream structure, which tends to overlook the intrinsic relationship between content and style motions.<n>We propose a Unified Motion Style Diffusion (UMSD) framework, which simultaneously extracts features from both content and style motions.<n>We also introduce the Motion Style Mamba (MSM) denoiser, the first approach in the field of motion style transfer to leverage Mamba's powerful sequence modelling capability.
  arXiv  Detail & Related papers  (2024-05-05T08:28:07Z)
• Diffusion-based Human Motion Style Transfer with Semantic Guidance [23.600154466988073]
  We propose a novel framework for few-shot style transfer learning based on the diffusion model. In the first stage, we pre-train a diffusion-based text-to-motion model as a generative prior. In the second stage, based on the single style example, we fine-tune the pre-trained diffusion model in a few-shot manner to make it capable of style transfer.
  arXiv  Detail & Related papers  (2024-03-20T05:52:11Z)
• HiCAST: Highly Customized Arbitrary Style Transfer with Adapter Enhanced Diffusion Models [84.12784265734238]
  The goal of Arbitrary Style Transfer (AST) is injecting the artistic features of a style reference into a given image/video. We propose HiCAST, which is capable of explicitly customizing the stylization results according to various source of semantic clues. A novel learning objective is leveraged for video diffusion model training, which significantly improve cross-frame temporal consistency.
  arXiv  Detail & Related papers  (2024-01-11T12:26:23Z)
• Priority-Centric Human Motion Generation in Discrete Latent Space [59.401128190423535]
  We introduce a Priority-Centric Motion Discrete Diffusion Model (M2DM) for text-to-motion generation. M2DM incorporates a global self-attention mechanism and a regularization term to counteract code collapse. We also present a motion discrete diffusion model that employs an innovative noise schedule, determined by the significance of each motion token.
  arXiv  Detail & Related papers  (2023-08-28T10:40:16Z)
• RSMT: Real-time Stylized Motion Transition for Characters [15.856276818061891]
  We propose a Real-time Stylized Motion Transition method (RSMT) to achieve all aforementioned goals. Our method consists of two critical, independent components: a general motion manifold model and a style motion sampler. Our method proves to be fast, high-quality, versatile, and controllable.
  arXiv  Detail & Related papers  (2023-06-21T01:50:04Z)
• A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning [84.8813842101747]
  Unified Contrastive Arbitrary Style Transfer (UCAST) is a novel style representation learning and transfer framework. We present an adaptive contrastive learning scheme for style transfer by introducing an input-dependent temperature. Our framework consists of three key components, i.e., a parallel contrastive learning scheme for style representation and style transfer, a domain enhancement module for effective learning of style distribution, and a generative network for style transfer.
  arXiv  Detail & Related papers  (2023-03-09T04:35:00Z)

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.