GuyTevet

motion-diffusion-model

The official PyTorch implementation of the paper "Human Motion Diffusion Model"

MotionCLIP

Official Pytorch implementation of the paper "MotionCLIP: Exposing Human Motion Generation to CLIP Space"

diversity-eval

Official Github repo for the paper "Evaluating the Evaluation of Diversity in Natural Language Generation"

mdm-page

Human Motion Diffusion Model - web page

smplx

SMPL-X - an FK only variant

ACTOR

Official Pytorch implementation of the paper "Action-Conditioned 3D Human Motion Synthesis with Transformer VAE", ICCV 2021

bert

TensorFlow code and pre-trained models for BERT

bert-sts

BERT_STS-B

body_visualizer

Visualization code for SMPL body model Family

cs294-158

Unsupervised Learning Spring 2019

ctrl

Conditional Transformer Language Model for Controllable Generation

deep-motion-editing

An end-to-end library for editing and rendering motion of 3D characters with deep learning [SIGGRAPH 2020]

DeepSDF

Learning Continuous Signed Distance Functions for Shape Representation

guytevet.github.io

Personal Webpage - based on https://jonbarron.info/

human-motion-prediction-pytorch

Simple baselines and RNNs for predicting human motion. Presented at CVPR 17. This pytorch implementation is based on the original one by the authors

language2pose-rep

Language2Pose: Natural Language Grounded Pose Forecasting

mas-page

MASS

MASS: Masked Sequence to Sequence Pre-training for Language Generation

mint

Multi-modal Content Creation Model Training Infrastructure including the FACT model (AI Choreographer) implementation.

moshpp

Motion and Shape Capture from Sparse Markers

motionclip-page

MotionCLIP project page

PARE

Code for ICCV2021 paper PARE: Part Attention Regressor for 3D Human Body Estimation

rnn-gan-eval

Code for training and evaluation of the model from "Language Generation with Recurrent Generative Adversarial Networks without Pre-training"

selfcontact

CVPR 2021 - Official code repository for the paper: On Self-Contact and Human Pose.

StyleCLIP

Exploring full body generation with StyleCLIP

t-vae

Transformer Variational Autoencoder experiment

torch-dct

DCT (discrete cosine transform) functions for pytorch

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

VIBE

Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"