Home

Awesome

PWC

Learnable Triangulation of Human Pose

This repository is an official PyTorch implementation of the paper "Learnable Triangulation of Human Pose" (ICCV 2019, oral). Here we tackle the problem of 3D human pose estimation from multiple cameras. We present 2 novel methods — Algebraic and Volumetric learnable triangulation — that outperform previous state of the art.

If you find a bug, have a question or know to improve the code - please open an issue!

:arrow_forward: ICCV 2019 talk

<p align="center"> <a href="http://www.youtube.com/watch?v=z3f3aPSuhqg"> <img width=680 src="docs/video-preview.jpg"> </a> </p>

How to use

This project doesn't have any special or difficult-to-install dependencies. All installation can be done with:

pip install -r requirements.txt

Data

Sorry, only Human3.6M dataset training/evaluation is available right now. We cannot add CMU Panoptic, sorry for that.

Human3.6M

  1. Download and preprocess the dataset by following the instructions in mvn/datasets/human36m_preprocessing/README.md.
  2. Download pretrained backbone's weights from here and place them here: ./data/pretrained/human36m/pose_resnet_4.5_pixels_human36m.pth (ResNet-152 trained on COCO dataset and finetuned jointly on MPII and Human3.6M).
  3. If you want to train Volumetric model, you need rough estimations of the pelvis' 3D positions both for train and val splits. In the paper we estimate them using the Algebraic model. You can use the pretrained Algebraic model to produce predictions or just take precalculated 3D skeletons.

Model zoo

In this section we collect pretrained models and configs. All pretrained weights and precalculated 3D skeletons can be downloaded at once from here and placed to ./data/pretrained, so that eval configs can work out-of-the-box (without additional setting of paths). Alternatively, the table below provides separate links to those files.

Human3.6M:

ModelTrain configEval configWeightsPrecalculated resultsMPJPE (relative to pelvis), mm
Algebraictrain/human36m_alg.yamleval/human36m_alg.yamllinktrain, val22.5
Volumetric (softmax)train/human36m_vol_softmax.yamleval/human36m_vol_softmax.yamllink20.4

Train

Every experiment is defined by .config files. Configs with experiments from the paper can be found in the ./experiments directory (see model zoo).

Single-GPU

To train a Volumetric model with softmax aggregation using 1 GPU, run:

python3 train.py \
  --config experiments/human36m/train/human36m_vol_softmax.yaml \
  --logdir ./logs

The training will start with the config file specified by --config, and logs (including tensorboard files) will be stored in --logdir.

Multi-GPU (in testing)

Multi-GPU training is implemented with PyTorch's DistributedDataParallel. It can be used both for single-machine and multi-machine (cluster) training. To run the processes use the PyTorch launch utility.

To train a Volumetric model with softmax aggregation using 2 GPUs on single machine, run:

python3 -m torch.distributed.launch --nproc_per_node=2 --master_port=2345 \
  train.py  \
  --config experiments/human36m/train/human36m_vol_softmax.yaml \
  --logdir ./logs

Tensorboard

To watch your experiments' progress, run tensorboard:

tensorboard --logdir ./logs

Evaluation

After training, you can evaluate the model. Inside the same config file, add path to the learned weights (they are dumped to logs dir during training):

model:
    init_weights: true
    checkpoint: {PATH_TO_WEIGHTS}

Also, you can change other config parameters like retain_every_n_frames_test.

Run:

python3 train.py \
  --eval --eval_dataset val \
  --config experiments/human36m/eval/human36m_vol_softmax.yaml \
  --logdir ./logs

Argument --eval_dataset can be val or train. Results can be seen in logs directory or in the tensorboard.

Results

Human3.6M

<br> MPJPE relative to pelvis:
MPJPE (averaged across all actions), mm
Multi-View Martinez [4]57.0
Pavlakos et al. [8]56.9
Tome et al. [4]52.8
Kadkhodamohammadi & Padoy [5]49.1
Qiu et al. [9]26.2
RANSAC (our implementation)27.4
Ours, algebraic22.4
Ours, volumetric20.5
<br> MPJPE absolute (scenes with invalid ground-truth annotations are excluded):
MPJPE (averaged across all actions), mm
RANSAC (our implementation)22.8
Ours, algebraic19.2
Ours, volumetric17.7
<br> MPJPE relative to pelvis (single-view methods):
MPJPE (averaged across all actions), mm
Martinez et al. [7]62.9
Sun et al. [6]49.6
Ours, volumetric single view49.9

CMU Panoptic

<br> MPJPE relative to pelvis [4 cameras]:
MPJPE, mm
RANSAC (our implementation)39.5
Ours, algebraic21.3
Ours, volumetric13.7

Method overview

We present 2 novel methods of learnable triangulation: Algebraic and Volumetric.

Algebraic

algebraic-model

Our first method is based on Algebraic triangulation. It is similar to the previous approaches, but differs in 2 critical aspects:

  1. It is fully differentiable. To achieve this, we use soft-argmax aggregation and triangulate keypoints via a differentiable SVD.
  2. The neural network additionally predicts scalar confidences for each joint, passed to the triangulation module, which successfully deals with outliers and occluded joints.

For the most popular Human3.6M dataset, this method already dramatically reduces error by 2.2 times (!), compared to the previous art.

Volumetric

volumetric-model

In Volumetric triangulation model, intermediate 2D feature maps are densely unprojected to the volumetric cube and then processed with a 3D-convolutional neural network. Unprojection operation allows dense aggregation from multiple views and the 3D-convolutional neural network is able to model implicit human pose prior.

Volumetric triangulation additionally improves accuracy, drastically reducing the previous state-of-the-art error by 2.4 times! Even compared to the best parallelly developed method by MSRA group, our method still offers significantly lower error of 21 mm.

<p align="center"> <img src="docs/unprojection.gif"> </p>

Cite us!

@inproceedings{iskakov2019learnable,
  title={Learnable Triangulation of Human Pose},
  author={Iskakov, Karim and Burkov, Egor and Lempitsky, Victor and Malkov, Yury},
  booktitle = {International Conference on Computer Vision (ICCV)},
  year={2019}
}

Contributors

News

References