SCALOR

This repository is the official implementation of "SCALOR: Generative World Models with Scalable Object Representations" by Jindong Jiang*, Sepehr Janghorbani*, Gerard de Melo, and Sungjin Ahn; accepted at the International Conference on Learning Representations (ICLR) 2020. Project Website

Requirements

To install requirements:

conda env create -f environment.yml

To activate:

conda activate scalor_env

Dataset

The "Grand Central Station" dataset can be downloaded here. After downloading the file, extract the dataset using this command:

tar -xf grandcentralframes.tar.gz -C /path/to/dataset/

Training

To train SCALOR with default settings, run this command:

python train.py --data-dir /path/to/dataset/

Results

Citation

@inproceedings{JiangJanghorbaniDeMeloAhn2020SCALOR,
  title={SCALOR: Generative World Models with Scalable Object Representations},
  author={Jindong Jiang and Sepehr Janghorbani and Gerard {de Melo} and Sungjin Ahn},
  booktitle={Proceedings of ICLR 2020},
  year={2020},
  publisher = {OpenReview.net},
  location = {Addis Ababa, Ethiopia},
  url = {https://openreview.net/pdf?id=SJxrKgStDH},
}