Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases

Mason, Ian; Starke, Sebastian; Komura, Taku

doi:10.48550/arxiv.2201.04439

Cited by 4 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…KM-CGs uses keyframes from the source domain as context constraints and employ Manifold Constrained Gradient (Chung et al 2022) to enforce these constraints during the second phase of DDIBs. Our experiments and quantative analysis on the 100STYLE (Mason, Starke, and Komura 2022) locomotion database, and the AIST++ (Tsuchida et al 2019) dance database find KMCGs achieves successful style transfer and better content preservation, reflected on the cycle consistency property on these two motion datasets and two probabilistic divergence-based metrics. Additionally, our human study as a subjective evaluation find samples generated from KMCGs are preferred in general.…”

Section: Introductionmentioning

confidence: 78%

Scalable Motion Style Transfer with Constrained Diffusion Generation

Yin,

Yu,

Yin

et al. 2024

AAAI

View full text Add to dashboard Cite

Current training of motion style transfer systems relies on consistency losses across style domains to preserve contents, hindering its scalable application to a large number of domains and private data. Recent image transfer works show the potential of independent training on each domain by leveraging implicit bridging between diffusion models, with the content preservation, however, limited to simple data patterns. We address this by imposing biased sampling in backward diffusion while maintaining the domain independence in the training stage. We construct the bias from the source domain keyframes and apply them as the gradient of content constraints, yielding a framework with keyframe manifold constraint gradients (KMCGs). Our validation demonstrates the success of training separate models to transfer between as many as ten dance motion styles. Comprehensive experiments find a significant improvement in preserving motion contents in comparison to baseline and ablative diffusion-based style transfer models. In addition, we perform a human study for a subjective assessment of the quality of generated dance motions. The results validate the competitiveness of KMCGs.

show abstract

Section: Introductionmentioning

confidence: 78%

Scalable Motion Style Transfer with Constrained Diffusion Generation

Yin,

Yu,

Yin

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…With per-frame user controls, the algorithm generates new stylized motions on the fly, in an autoregressive fashion. A similar work on this topic is [12].…”

Section: Introductionmentioning

confidence: 90%

Online Motion Style Transfer for Interactive Character Control

Tang¹,

Liu²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Motion style transfer is highly desired for motion generation systems for gaming. Compared to its offline counterpart, the research on online motion style transfer under interactive control is limited. In this work, we propose an end-to-end neural network that can generate motions with different styles and transfer motion styles in real-time under user control. Our approach eliminates the use of handcrafted phase features, and could be easily trained and directly deployed in game systems. In the experiment part, we evaluate our approach from three aspects that are essential for industrial game design: accuracy, flexibility, and variety, and our model performs a satisfying result.

show abstract

“…Henter et al [2020] propose another generative model for motion based on normalizing flow. Neural networks succeed in a variety of motion generation tasks: motion retargeting [Aberman et al 2020a[Aberman et al , 2019Villegas et al 2018], motion style transfer [Aberman et al 2020b;Mason et al 2022], key-frame based motion generation [Harvey et al 2020], motion matching [Holden et al 2020] and animation layering [Starke et al 2021]. It is worth noting that the success of deep learning methods hinges upon large and comprehensive mocap datasets.…”

Section: Related Workmentioning

confidence: 99%

GANimator: Neural Motion Synthesis from a Single Sequence

Li,

Aberman,

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

Fig. 1. Given a single training motion sequence of skeleton with arbitrary topology, our method learns to synthesize novel motion sequences.We present GANimator, a generative model that learns to synthesize novel motions from a single, short motion sequence. GANimator generates motions that resemble the core elements of the original motion, while simultaneously synthesizing novel and diverse movements. Existing data-driven techniques for motion synthesis require a large motion dataset which contains the desired and specific skeletal structure. By contrast, GANimator only requires training on a single motion sequence, enabling novel motion synthesis for a variety of skeletal structures e.g., bipeds, quadropeds, hexapeds, and more. Our framework contains a series of generative and adversarial neural networks, each responsible for generating motions in a specific frame rate. The framework progressively learns to synthesize motion from random noise, enabling hierarchical control over the generated motion content across varying levels of detail. We show a number of applications, including crowd simulation, key-frame editing, style transfer, and interactive control, which all learn from a single input sequence. Code and data for this paper are at https://peizhuoli.github.io/ganimator. CCS Concepts: • Computing methodologies → Motion processing; Machine learning approaches.

show abstract

Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases

Cited by 4 publications

References 36 publications

Scalable Motion Style Transfer with Constrained Diffusion Generation

Scalable Motion Style Transfer with Constrained Diffusion Generation

Online Motion Style Transfer for Interactive Character Control

GANimator: Neural Motion Synthesis from a Single Sequence

Contact Info

Product

Resources

About