Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
data
models
src
.gitignore
LICENSE
readme.md

readme.md

Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency

This repository is the PyTorch implementation for the network presented in:

Xingyi Zhou, Arjun Karpur, Chuang Gan, Linjie Luo, Qixing Huang, Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency ECCV 2018(arXiv:1712.05765)

Contact: zhouxy2017@gmail.com

Requirements

Data

  • The following datasets are used in this repo. If you use the data provided, please also consider citing them:
  • Download the pre-processing data and annotations here, and un-zip them on data.

Testing

  • Download our pre-trained model on Redwood Depth dataset and move it to models.
  • Run the test.
 python main.py -expID demo -loadModel ../models/Redwood.pth.tar -test
  • Visualize the results.
python tools/vis.py ../exp/Chair/demo/img_valTarget ../exp/Chair/demo/valTarget.txt

Training

  • Stage1: Train the source model.
python main.py -expID Source -epochs 120 -dropLR 90

Our results of this stage is provided here.

  • Stage2: Adapt to the target domain with shape consistency loss.
python main.py -expID Redwood -targetDataset Redwood -targetRatio 1 -shapeWeight 1 -loadModel ../models/ModelNet120.tar -LR 0.01