A very simple baseline to estimate 2D & 3D SMPL-compatible keypoints from a single color image.

Last update: Dec 05, 2022

Overview

Minimal Body

A very simple baseline to estimate 2D & 3D SMPL-compatible keypoints from a single color image.

The model file is only 51.2 MB and runs at 70fps on a 2080Ti.

Usage

Download the pre-trained model here into model/.
Install the dependencies.
Run python example.py.

The model is trained using the following datasets jointly:

Please also check the license of the listed datasets.

If you find it helpful, please consider citing our related paper:

@InProceedings{Zhou_2021_CVPR,
    author    = {Zhou, Yuxiao and Habermann, Marc and Habibie, Ikhsanul and Tewari, Ayush and Theobalt, Christian and Xu, Feng},
    title     = {Monocular Real-Time Full Body Capture With Inter-Part Correlations},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {4811-4822}
}

You might also like...

SMPL-X: A new joint 3D model of the human body, face and hands together

SMPL-X: A new joint 3D model of the human body, face and hands together [Paper Page] [Paper] [Supp. Mat.] Table of Contents License Description News I

1k Jan 9, 2023

Solving SMPL/MANO parameters from keypoint coordinates.

Minimal-IK A simple and naive inverse kinematics solver for MANO hand model, SMPL body model, and SMPL-H body+hand model. Briefly, given joint coordin

305 Dec 30, 2022

Accelerated SMPL operation, commonly used in generate 3D human mesh, STAR included.

SMPL2 An enchanced and accelerated SMPL operation which commonly used in 3D human mesh generation. It takes a poses, shapes, cam_trans as inputs, outp

20 Oct 17, 2022

A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run.

Minimal Hand A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run. This project provides the

824 Jan 7, 2023

Learning to Estimate Hidden Motions with Global Motion Aggregation

Learning to Estimate Hidden Motions with Global Motion Aggregation (GMA) This repository contains the source code for our paper: Learning to Estimate

221 Dec 18, 2022

A deep learning network built with TensorFlow and Keras to classify gender and estimate age.

Convolutional Neural Network (CNN). This repository contains a source code of a deep learning network built with TensorFlow and Keras to classify gend

1 Dec 18, 2021

A deep learning network built with TensorFlow and Keras to classify gender and estimate age.

Convolutional Neural Network (CNN). This repository contains a source code of a deep learning network built with TensorFlow and Keras to classify gend

1 Dec 19, 2021

Official Pytorch implementation of "Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes", CVPR 2022

Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes / 3DCrowdNet News 💪 3DCrowdNet achieves the state-of-the-art accuracy on 3D

113 Dec 21, 2022

Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps[AAAI2021]

Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps Here is the code for ssbassline model. We also provide OCR results/features/mode

51 Nov 18, 2022

Comments

About light-weight human detector

Very interesting model! Since this model takes croped human as input, may I ask if there is any realtime human detector recommend that is light-weight to work with this model together? Thank you~

opened by Garfield-kh 2
About the whole model ?

Hey, it is a very great work. By the way, is there any plan for releasing the whole model? What's more, is there any plan for releasing the training code?

opened by maitetsu 2

Releases(v1)

v1(Nov 19, 2021)

The original version.
Source code(tar.gz)
Source code(zip)
minimal_body_v1.pth(51.22 MB)

Owner

Yuxiao Zhou

Good luck, have fun.

GitHub Repository

Pytorch codes for Feature Transfer Learning for Face Recognition with Under-Represented Data

FTLNet_Pytorch Pytorch codes for Feature Transfer Learning for Face Recognition with Under-Represented Data 1. Introduction This repo is an unofficial

1 Nov 04, 2020

The project is associated with the recently-launched ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) to provide participants with baseline systems for speech recognition and speaker diarization in conference scenario.

M2MeT challenge baseline -- AliMeeting This project provides the baseline system recipes for the ICASSP 2020 Multi-channel Multi-party Meeting Transcr

81 Dec 08, 2022

torchbearer: A model fitting library for PyTorch

Note: We're moving to PyTorch Lightning! Read about the move here. From the end of February, torchbearer will no longer be actively maintained. We'll

632 Dec 13, 2022

Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

PyTorch Implementation of Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers 1 Using Colab Please notic

489 Jan 07, 2023

Pytorch Implementation of DiffSinger: Diffusion Acoustic Model for Singing Voice Synthesis (TTS Extension)

DiffSinger - PyTorch Implementation PyTorch implementation of DiffSinger: Diffusion Acoustic Model for Singing Voice Synthesis (TTS Extension). Status

152 Jan 02, 2023

Object detection using yolo-tiny model and opencv used as backend

Object detection Algorithm used : Yolo algorithm Backend : opencv Library required: opencv = 4.5.4-dev' Quick Overview about structure 1) main.py Load

2 Jul 06, 2022

You Only 👀 One Sequence

You Only 👀 One Sequence TL;DR: We study the transferability of the vanilla ViT pre-trained on mid-sized ImageNet-1k to the more challenging COCO obje

666 Jan 03, 2023

[arXiv'22] Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation

Panoptic NeRF Project Page | Paper | Dataset Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation Xiao Fu*, Shangzhan zhang*,

111 Dec 16, 2022

Federated Learning - Including common test models for federated learning, like CNN, Resnet18 and lstm, controlled by different parser

Federated_Learning 💻 This projest include common test models for federated lear

10 Dec 11, 2022

A very simple baseline to estimate 2D & 3D SMPL-compatible keypoints from a single color image.

Related tags

Overview

Minimal Body

Usage

You might also like...

SMPL-X: A new joint 3D model of the human body, face and hands together

Solving SMPL/MANO parameters from keypoint coordinates.

Accelerated SMPL operation, commonly used in generate 3D human mesh, STAR included.

A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run.

Learning to Estimate Hidden Motions with Global Motion Aggregation

A deep learning network built with TensorFlow and Keras to classify gender and estimate age.

A deep learning network built with TensorFlow and Keras to classify gender and estimate age.

Official Pytorch implementation of "Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes", CVPR 2022

Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps[AAAI2021]

Comments

About light-weight human detector

About the whole model ?

Releases(v1)

v1(Nov 19, 2021)

Owner

Yuxiao Zhou

Pytorch codes for Feature Transfer Learning for Face Recognition with Under-Represented Data

The project is associated with the recently-launched ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) to provide participants with baseline systems for speech recognition and speaker diarization in conference scenario.

torchbearer: A model fitting library for PyTorch

Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

Pytorch Implementation of DiffSinger: Diffusion Acoustic Model for Singing Voice Synthesis (TTS Extension)

Object detection using yolo-tiny model and opencv used as backend

You Only 👀 One Sequence

[arXiv'22] Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation

Federated Learning - Including common test models for federated learning, like CNN, Resnet18 and lstm, controlled by different parser

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

Artstation-Artistic-face-HQ Dataset (AAHQ)

Code and training data for our ECCV 2016 paper on Unsupervised Learning

AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition

DiffStride: Learning strides in convolutional neural networks

Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition

Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data

Universal Probability Distributions with Optimal Transport and Convex Optimization

Use tensorflow to implement a Deep Neural Network for real time lane detection

Unofficial implement with paper SpeakerGAN: Speaker identification with conditional generative adversarial network

Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies