Skip to content

Latest commit

 

History

History
37 lines (30 loc) · 1.16 KB

README.md

File metadata and controls

37 lines (30 loc) · 1.16 KB
Raw

Official Implementation of SeqHand

This is the implementation of synthetic hand motion generation presented in SeqHAND (ECCV 2020).

Required Libraries

pytorch==1.3.1
cv2==3.4.2
imageio==2.6.1
pickle
os
pillow==6.1.0
numpy
opendr>=0.76
tqdm

BH-dataset

I have normalized BigHand dataset annotations (3D joint coordinates for each pose data). You need to get this normalized BigHand data file and save at your project directory in order to generate hand motions.

MANO

Install and set up manopth (MANO library) as explained in their work page.

Put your "mano" folder in /your/project/directory/mano/.

Hand Skin Color

Hand skin colors (meshes_colored/) are obtained from our baseline work

Usage

In order to generate RGB hand motion image samples, run

python gen_sequential_synth_data.py

The genrations are saved in results/ folder.