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 Wolf1,2
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.