computer-code-3

Motion Synthesis

3260 papers • 126 benchmarks • 313 datasets

Image source: Multi-View Motion Synthesis via Applying Rotated Dual-Pixel Blur Kernels

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in motion-synthesis-7

Trend

Dataset

Best Model

Actions

HumanML3D

KIT Motion-Language

AIST++

Libraries

i

Use these libraries to find motion-synthesis-7 models and implementations

Datasets

Subtasks

Motion Style Transfer Temporal Human Motion Composition

Most implemented papers

On Human Motion Prediction Using Recurrent Neural Networks

Julieta Martinez, Michael J. Black, J. Romero•Fri May 05 2017

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.

997

Content

FineDance

LaFAN1

BRACE

HumanAct12

Trinity Speech-Gesture Dataset

BRACE

LaFAN1

CHAIRS dataset

Trinity Speech-Gesture Dataset

0

Paper Graph

HP-GAN: Probabilistic 3D Human Motion Prediction via GAN

Zicheng Liu, E. Barsoum, J. Kender•Sun Nov 26 2017

A novel sequence-to-sequence model for probabilistic human motion prediction, trained with a modified version of improved Wasserstein generative adversarial networks (WGAN-GP), in which the model learns a probability density function of future human poses conditioned on previous poses.

362 0

Paper Graph

Multi-View Motion Synthesis via Applying Rotated Dual-Pixel Blur Kernels

M. Afifi, Abdullah Abuolaim, Michael S. Brown•Sun Nov 14 2021

This work follows the trend of rendering the NIMAT effect by introducing a modification on the blur synthesis procedure in portrait mode that enables a high-quality synthesis of multi-view bokeh from a single image by applying rotated blurring kernels.

4 0

Paper Graph

Dancing to Music

Ming-Hsuan Yang, Jan Kautz, Xiaodong Yang, Hsin-Ying Lee, Ting-Chun Wang, Ming-Yu Liu, Yu-Ding Lu•Mon Nov 04 2019

Experimental qualitative and quantitative results demonstrate that the proposed synthesis-by-analysis learning framework can synthesize realistic, diverse, style-consistent, and beat-matching dances from music.

15 0

Paper Graph

Action-Conditioned 3D Human Motion Synthesis with Transformer VAE

Michael J. Black, Mathis Petrovich, Gul Varol•Sun Apr 11 2021

This work designs a Transformer-based architecture, ACTOR, for encoding and decoding a sequence of parametric SMPL human body models estimated from action recognition datasets, and learns an action-aware latent representation for human motions by training a generative variational autoencoder (VAE).

628 0

Paper Graph

MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement

Yandong Wen, F. D. L. Torre, Alexander Richard, Yaser Sheikh, Michael Zollhoefer•Thu Apr 15 2021

A generic audio-driven facial animation approach that achieves highly realistic motion synthesis results for the entire face by disentangles audio-correlated and audio-uncorrelated information based on a novel cross-modality loss.

253 0

Paper Graph

MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model

Mingyuan Zhang, Xinying Guo, Liang Pan, Zhongang Cai, Fangzhou Hong, Lei Yang, Ziwei Liu•Tue Aug 30 2022

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.

819 0

Paper Graph

Human Motion Diffusion as a Generative Prior

Amit H. Bermano, Yonatan Shafir, Guy Tevet, Roy Kapon•Wed Mar 01 2023

This paper introduces three forms of composition based on diffusion priors: sequential, parallel, and model composition, and introduces DiffusionBlending, an interpolation mechanism to effectively blend several such models to enable flexible and efficient fine-grained joint and trajectory-level control and editing.

329 0

Paper Graph

Adding a benchmark result helps the community track progress.