ml-lab / scene_generation

A PyTorch implementation of the paper: Specifying Object Attributes and Relations in Interactive Scene Generation

Specifying Object Attributes and Relations in Interactive Scene Generation

A PyTorch implementation of Specifying Object Attributes and Relations in Interactive Scene Generation

Paper

Specifying Object Attributes and Relations in Interactive Scene Generation
Oron Ashual¹, Lior Wolf^1,2
1 Tel-Aviv University, ² Facebook AI Research
IEEE International Conference on Computer Vision (ICCV), 2019, (Oral)

Network Architechture

Youtube

Usage

1. Creating virtual environment (optional)

All code was developed and tested on Ubuntu 18.04 with Python 3.6 (Anaconda) and PyTorch 1.0.

$ conda create -n scene_generation python=3.6
$ conda activate scene_generation

2. Install COCO API

$ cd ~
$ git clone https://github.com/cocodataset/cocoapi.git
$ cd cocoapi/PythonAPI/
$ python setup.py install
$ cd ..

3. Cloning the repository

$ git clone [email protected]:ashual/scene_generation.git
$ cd scene_generation

4. Installing dependencies

$ conda install -r requirements.txt

5. Training

$ python train.py

6. Downloading trained models

TBD

7. GUI

The GUI was built as POC. For using it run:

python scripts/gui/simple-server.py --checkpoint YOUR_MODEL_CHECKPOINT

Citation

If you find this code useful in your research then please cite

@inproceedings{ashual2019scenegeneration,
  title={Specifying Object Attributes and Relations in Interactive Scene Generation},
  author={Ashual, Oron and Wolf, Lior},
  booktitle={ICCV},
  year={2019}
}

Acknowledgement

Our project borrows some source files from sg2im. We thank the authors.