Skip to content

Latest commit

 

History

History
31 lines (24 loc) · 1.39 KB

README.md

File metadata and controls

31 lines (24 loc) · 1.39 KB

DUST-net

Code for the Distributional Depth-Based Estimation of Object Articulation Models paper presented at the 5th Annual Conference on Robot Learning (CoRL), 2021. Full paper available here. [Project webpage]

Instructions to run the code

Installing prerequisites and environment

conda env create -f env.yaml
conda activate dustnet
cd /path/to/the/repository/

Downloading datasets and pretrained model weights

  • Evaluation datasets: Link
  • Pretrained weights: Link

Running the evaluation script

python evaluate_model.py --model-dir <pretrained-model-dir> --model-name <model-name> --test-file <test-dir-name> --model-type <vm-ortho, vm-st, vm-st-svd> --output-dir <output-dir>

[Optional] Training on custom dataset

  • Generate dataset using our fork of the Synthetic articulated dataset generator from here.
  • Run the following command to train DUST-net on the generated datasets
TO BE INCLUDED SOON

Contact

In case of any questions or queries, please feel free to contact Ajinkya Jain.