[PDF] Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models | Semantic Scholar (2024)

[PDF] Semantic Reader

This work constructs the bias from the source domain keyframes and applies them as the gradient of content constraints, yielding a framework with keyframe manifold constraint gradients (KMCGs) and performs a human study for a subjective assessment of the quality of generated dance motions.

A probabilistic generative model is proposed to synthesize and reconstruct long horizon motion sequences conditioned on past information and control signals, such as the path along which an individual is moving, to reconstructing missing markers and achieving comparable results on generating realistic future poses.

A novel generative model of human motion that can be trained using a large motion capture dataset, and allows users to produce animations from high-level control signals that can predict the movements of the human body over long horizons more accurately than state-of-the-art methods.

A new generative deep learning network for human motion synthesis and control that is compact, contact-aware, and can generate an infinite number of naturally looking motions with infinite lengths is introduced.

Motion Diffusion Model (MDM), a carefully adapted classifier-free diffusion-based generative model for the human motion domain, is introduced, a transformer-based approach, enabling different modes of conditioning, and different generation tasks.

This work adapts the DiffWave architecture to model 3D pose sequences, putting Conformers in place of dilated convolutions for improved modelling power and demonstrates control over motion style, using classifier-free guidance to adjust the strength of the stylistic expression.

It is shown that, surprisingly, state of the art performance can be achieved by a simple baseline that does not attempt to model motion at all, and a simple and scalable RNN architecture is proposed that obtains state-of-the-art performance on human motion prediction.

BeLFusion is a model that, for the first time, leverages latent diffusion models in HMP to sample from a behavioral latent space where behavior is disentangled from pose and motion, and its predictions display a variety of behaviors that are significantly more realistic, and coherent with past motion than the state of the art.

This work is the first to the knowledge that demonstrates the ability to generate over 18,000 continuous frames (300 seconds) of new complex human motion w.r.t. different styles.

The proposed MotionDiffuse is one of the first diffusion model-based text-driven motion generation frameworks, which demonstrates several desired properties over existing methods, and outperforms existing SoTA methods by convincing margins on text-driven motion generation and action-conditioned motion generation.

The results show that deep feedforward networks, trained from a generic mocap database, can successfully be used for feature extraction from human motion data and that this representation can be used as a foundation for classification and prediction.

...

...