-
Fraunhofer HHI
- Berlin
- ujemd.github.io/resume/
Stars
Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"
Google Research
Google Drive Public File Downloader when Curl/Wget Fails
Project for paper "Learning 3D Human Dynamics from Video"
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
A python library for highly configurable transformers - easing model architecture search and experimentation.
Audio2Motion Official implementation for Audio2Motion: Generating Diverse Gestures from Speech with Conditional Variational Autoencoders.
VPoser: Variational Human Pose Prior
Solving SMPL/MANO parameters from keypoint coordinates.
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
Collection of common code that's shared among different research projects in FAIR computer vision team.
Implementation of ConvMixer for "Patches Are All You Need? 🤷"
torch-optimizer -- collection of optimizers for Pytorch
Implementation of Fast Transformer in Pytorch
Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021
Experiments for understanding disentanglement in VAE latent representations
Vector (and Scalar) Quantization, in Pytorch
This is the official implementation for IVA '19 paper "Analyzing Input and Output Representations for Speech-Driven Gesture Generation".
SGToolkit: An Interactive Gesture Authoring Toolkit for Embodied Conversational Agents (UIST 2021)
Unofficial implementation of Alias-Free Generative Adversarial Networks. (https://arxiv.org/abs/2106.12423) in PyTorch
PyTorch implementation of FNet: Mixing Tokens with Fourier transforms
💫 Industrial-strength Natural Language Processing (NLP) in Python
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.