Skip to content
/ DLow Public

[ECCV 2020] Official PyTorch Implementation of "DLow: Diversifying Latent Flows for Diverse Human Motion Prediction". ECCV 2020.


Notifications You must be signed in to change notification settings


Folders and files

Last commit message
Last commit date

Latest commit



7 Commits

Repository files navigation

DLow: Diversifying Latent FLows

Loading DLow Overview

This repo contains the official implementation of our paper:

DLow: Diversifying Latent Flows for Diverse Human Motion Prediction
Ye Yuan, Kris Kitani
ECCV 2020
[website] [paper] [talk] [summary] [demo]



  • Please follow the data preprocessing steps ( inside the VideoPose3D repo. Place the prepocessed data data_3d_h36m.npz (Human3.6M) and data_3d_humaneva15.npz (HumanEva-I) under the data folder.


  • Tested OS: MacOS, Linux
  • Packages:
    • Python >= 3.6
    • PyTorch >= 0.4
    • Tensorboard
  • Note: All scripts should be run from the root of this repo to avoid path issues.

Pretrained Models

  • Download our pretrained models from Google Drive (or BaiduYun, password: y9ph) and place the unzipped results folder inside the root of this repo.



We have provided 4 example YAML configs inside motion_pred/cfg:

  • h36m_nsamp10.yml and h36m_nsamp50.yml for Human3.6M for number of samples 10 and 50 respectively.
  • humaneva_nsamp10.yml and humaneva_nsamp50.yml for HumanEva-I for number of samples 10 and 50 respectively.
  • These configs also have corresponding pretrained models inside results.

Train VAE

python motion_pred/ --cfg h36m_nsamp10

Train DLow (After VAE is trained)

python motion_pred/ --cfg h36m_nsamp10


Visualize Motion Samples

python motion_pred/ --cfg h36m_nsamp10 --mode vis

Useful keyboard shortcuts for the visualization GUI:

Key Functionality
d test next motion data
c save current animation as out/video.mp4
space stop/resume animation
1 show DLow motion samples
2 show VAE motion samples

Compute Metrics

python motion_pred/ --cfg h36m_nsamp50 --mode stats


If you find our work useful in your research, please cite our paper DLow:

    title={Dlow: Diversifying latent flows for diverse human motion prediction},
    author={Yuan, Ye and Kitani, Kris},
    booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},


Part of the code is borrowed from the VideoPose3D repo.


The software in this repo is freely available for free non-commercial use. Please see the license for further details.