All Projects → mkocabas → Vibe

mkocabas / Vibe

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

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Projects that are alternatives of or similar to Vibe

MEVA
Official implementation of ACCV 2020 paper "3D Human Motion Estimation via Motion Compression and Refinement" (Identical repo to https://github.com/KlabCMU/MEVA, will be kept in sync)
Stars: ✭ 93 (-95.53%)
Mutual labels:  human-pose-estimation, 3d-human-pose, 3d-pose-estimation, smpl
HybrIK
Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021
Stars: ✭ 395 (-81.01%)
Mutual labels:  cvpr, 3d-pose-estimation, smpl
metro-pose3d
Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation
Stars: ✭ 51 (-97.55%)
Mutual labels:  human-pose-estimation, 3d-human-pose
PyMAF
[ICCV21, Oral] PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop
Stars: ✭ 333 (-83.99%)
Mutual labels:  3d-human-pose, smpl
deep cage
code for "Neural Cages for Detail-Preserving 3D Deformations"
Stars: ✭ 115 (-94.47%)
Mutual labels:  cvpr, cvpr2020
CVPR-2020-point-cloud-analysis
CVPR 2020 papers focusing on point cloud analysis
Stars: ✭ 48 (-97.69%)
Mutual labels:  cvpr, cvpr2020
Evoskeleton
Official project website for the CVPR 2020 paper (Oral Presentation) "Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training Data"
Stars: ✭ 154 (-92.6%)
Mutual labels:  human-pose-estimation, cvpr
pytorch-psetae
PyTorch implementation of the model presented in "Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention"
Stars: ✭ 117 (-94.37%)
Mutual labels:  cvpr, cvpr2020
Awesome Human Pose Estimation
A collection of awesome resources in Human Pose estimation.
Stars: ✭ 2,022 (-2.79%)
Mutual labels:  human-pose-estimation, 3d-human-pose
Meta-Fine-Tuning
[CVPR 2020 VL3] The repository for meta fine-tuning in cross-domain few-shot learning.
Stars: ✭ 29 (-98.61%)
Mutual labels:  cvpr, cvpr2020
pcv
Pixel Consensus Voting for Panoptic Segmentation (CVPR 2020)
Stars: ✭ 23 (-98.89%)
Mutual labels:  cvpr, cvpr2020
BOA
Bilevel Online Adaptation for Human Mesh Reconstruction
Stars: ✭ 43 (-97.93%)
Mutual labels:  human-pose-estimation, smpl
LUVLi
[CVPR 2020] Re-hosting of the LUVLi Face Alignment codebase. Please download the codebase from the original MERL website by agreeing to all terms and conditions. By using this code, you agree to MERL's research-only licensing terms.
Stars: ✭ 24 (-98.85%)
Mutual labels:  cvpr, cvpr2020
SCT
SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation (CVPR2020) https://arxiv.org/abs/2003.14266
Stars: ✭ 35 (-98.32%)
Mutual labels:  cvpr, cvpr2020
Cvpr2021 Papers With Code
CVPR 2021 论文和开源项目合集
Stars: ✭ 7,138 (+243.17%)
Mutual labels:  cvpr, cvpr2020
ICON
ICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)
Stars: ✭ 641 (-69.18%)
Mutual labels:  human-pose-estimation, smpl
attention-target-detection
[CVPR2020] "Detecting Attended Visual Targets in Video"
Stars: ✭ 105 (-94.95%)
Mutual labels:  cvpr, cvpr2020
HiCMD
[CVPR2020] Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification
Stars: ✭ 64 (-96.92%)
Mutual labels:  cvpr, cvpr2020
Epipolarpose
Self-Supervised Learning of 3D Human Pose using Multi-view Geometry (CVPR2019)
Stars: ✭ 477 (-77.07%)
Mutual labels:  human-pose-estimation, cvpr
Dhf1k
Revisiting Video Saliency: A Large-scale Benchmark and a New Model (CVPR18, PAMI19)
Stars: ✭ 96 (-95.38%)
Mutual labels:  cvpr

VIBE: Video Inference for Human Body Pose and Shape Estimation [CVPR-2020]

report Open In Colab PWC

Check our YouTube videos below for more details.

Paper Video Qualitative Results
PaperVideo QualitativeResults

VIBE: Video Inference for Human Body Pose and Shape Estimation,
Muhammed Kocabas, Nikos Athanasiou, Michael J. Black,
IEEE Computer Vision and Pattern Recognition, 2020

Features

Video Inference for Body Pose and Shape Estimation (VIBE) is a video pose and shape estimation method. It predicts the parameters of SMPL body model for each frame of an input video. Pleaser refer to our arXiv report for further details.

This implementation:

  • has the demo and training code for VIBE implemented purely in PyTorch,
  • can work on arbitrary videos with multiple people,
  • supports both CPU and GPU inference (though GPU is way faster),
  • is fast, up-to 30 FPS on a RTX2080Ti (see this table),
  • achieves SOTA results on 3DPW and MPI-INF-3DHP datasets,
  • includes Temporal SMPLify implementation.
  • includes the training code and detailed instruction on how to train it from scratch.
  • can create an FBX/glTF output to be used with major graphics softwares.

Updates

  • 05/01/2021: Windows installation tutorial is added thanks to amazing @carlosedubarreto
  • 06/10/2020: Support OneEuroFilter smoothing.
  • 14/09/2020: FBX/glTF conversion script is released.

Getting Started

VIBE has been implemented and tested on Ubuntu 18.04 with python >= 3.7. It supports both GPU and CPU inference. If you don't have a suitable device, try running our Colab demo.

Clone the repo:

git clone https://github.com/mkocabas/VIBE.git

Install the requirements using virtualenv or conda:

# pip
source scripts/install_pip.sh

# conda
source scripts/install_conda.sh

Running the Demo

We have prepared a nice demo code to run VIBE on arbitrary videos. First, you need download the required data(i.e our trained model and SMPL model parameters). To do this you can just run:

source scripts/prepare_data.sh

Then, running the demo is as simple as:

# Run on a local video
python demo.py --vid_file sample_video.mp4 --output_folder output/ --display

# Run on a YouTube video
python demo.py --vid_file https://www.youtube.com/watch?v=wPZP8Bwxplo --output_folder output/ --display

Refer to doc/demo.md for more details about the demo code.

Sample demo output with the --sideview flag:

FBX and glTF output (New Feature!)

We provide a script to convert VIBE output to standalone FBX/glTF files to be used in 3D graphics tools like Blender, Unity etc. You need to follow steps below to be able to run the conversion script.

  • You need to download FBX files for SMPL body model
    • Go to SMPL website and create an account.
    • Download the Unity-compatible FBX file through the link
    • Unzip the contents and locate them data/SMPL_unity_v.1.0.0.
  • Install Blender python API
    • Note that we tested our script with Blender v2.8.0 and v2.8.3.
  • Run the command below to convert VIBE output to FBX:
python lib/utils/fbx_output.py \
    --input output/sample_video/vibe_output.pkl \
    --output output/sample_video/fbx_output.fbx \ # specify the file extension as *.glb for glTF
    --fps_source 30 \
    --fps_target 30 \
    --gender <male or female> \
    --person_id <tracklet id from VIBE output>

Windows Installation Tutorial

You can follow the instructions provided by @carlosedubarreto to install and run VIBE on a Windows machine:

Google Colab

If you do not have a suitable environment to run this project then you could give Google Colab a try. It allows you to run the project in the cloud, free of charge. You may try our Colab demo using the notebook we have prepared: Open In Colab

Training

Run the commands below to start training:

source scripts/prepare_training_data.sh
python train.py --cfg configs/config.yaml

Note that the training datasets should be downloaded and prepared before running data processing script. Please see doc/train.md for details on how to prepare them.

Evaluation

Here we compare VIBE with recent state-of-the-art methods on 3D pose estimation datasets. Evaluation metric is Procrustes Aligned Mean Per Joint Position Error (PA-MPJPE) in mm.

Models 3DPW ↓ MPI-INF-3DHP ↓ H36M ↓
SPIN 59.2 67.5 41.1
Temporal HMR 76.7 89.8 56.8
VIBE 56.5 63.4 41.5

See doc/eval.md to reproduce the results in this table or evaluate a pretrained model.

Correction: Due to a mistake in dataset preprocessing, VIBE trained with 3DPW results in Table 1 of the original paper are not correct. Besides, even though training with 3DPW guarantees better quantitative performance, it does not give good qualitative results. ArXiv version will be updated with the corrected results.

Citation

@inproceedings{kocabas2019vibe,
  title={VIBE: Video Inference for Human Body Pose and Shape Estimation},
  author={Kocabas, Muhammed and Athanasiou, Nikos and Black, Michael J.},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = {June},
  year = {2020}
}

License

This code is available for non-commercial scientific research purposes as defined in the LICENSE file. By downloading and using this code you agree to the terms in the LICENSE. Third-party datasets and software are subject to their respective licenses.

References

We indicate if a function or script is borrowed externally inside each file. Here are some great resources we benefit:

  • Pretrained HMR and some functions are borrowed from SPIN.
  • SMPL models and layer is from SMPL-X model.
  • Some functions are borrowed from Temporal HMR.
  • Some functions are borrowed from HMR-pytorch.
  • Some functions are borrowed from Kornia.
  • Pose tracker is from STAF.
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].