Motion Synthesis
89 papers with code • 9 benchmarks • 13 datasets
Benchmarks
These leaderboards are used to track progress in Motion Synthesis
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Datasets
HumanML3D
KIT Motion-Language
HumanAct12
AIST++
InterHuman
BRACE
LaFAN1
Most implemented papers
On human motion prediction using recurrent neural networks
una-dinosauria/human-motion-prediction
•
•
CVPR 2017
Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented reality.
DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
xbpeng/DeepMimic
•
•
We further explore a number of methods for integrating multiple clips into the learning process to develop multi-skilled agents capable of performing a rich repertoire of diverse skills.
HP-GAN: Probabilistic 3D human motion prediction via GAN
ebarsoum/hpgan
•
•
Our model, which we call HP-GAN, learns a probability density function of future human poses conditioned on previous poses.
MoGlow: Probabilistic and controllable motion synthesis using normalising flows
Data-driven modelling and synthesis of motion is an active research area with applications that include animation, games, and social robotics.
Multi-View Motion Synthesis via Applying Rotated Dual-Pixel Blur Kernels
Abdullah-Abuolaim/defocus-deblurring-dual-pixel
•
•
In this work, we follow the trend of rendering the NIMAT effect by introducing a modification on the blur synthesis procedure in portrait mode.
Dancing to Music
NVlabs/Dance2Music
•
•
NeurIPS 2019
In the analysis phase, we decompose a dance into a series of basic dance units, through which the model learns how to move.
Action-Conditioned 3D Human Motion Synthesis with Transformer VAE
By sampling from this latent space and querying a certain duration through a series of positional encodings, we synthesize variable-length motion sequences conditioned on a categorical action.
MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement
facebookresearch/meshtalk
•
•
ICCV 2021
To improve upon existing models, we propose a generic audio-driven facial animation approach that achieves highly realistic motion synthesis results for the entire face.
MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
mingyuan-zhang/MotionDiffuse
•
•
Instead of a deterministic language-motion mapping, MotionDiffuse generates motions through a series of denoising steps in which variations are injected.
Human Motion Diffusion as a Generative Prior
We evaluate the composition methods using an off-the-shelf motion diffusion model, and further compare the results to dedicated models trained for these specific tasks.
