Keep Drawing It: Iterative language-based image generation and editing
Abstract
Conditional text-to-image generation approaches commonly focus on generating a single image in a single step. One practical extension beyond one-step generation is an interactive system that generates an image iteratively, conditioned on ongoing linguistic input / feedback. This is significantly more challenging as such a system must understand and keep track of the ongoing context and history. In this work, we present a recurrent image generation model which takes into account both the generated output up to the current step as well as all past instructions for generation. We show that our model is able to generate the background, add new objects, apply simple transformations to existing objects, and correct previous mistakes. We believe our approach is an important step toward interactive generation.
BibTeX
@inproceedings{elnouby2018keepdrawingit,
title = {Keep Drawing It: Iterative language-based image generation and editing},
author = {El{-}Nouby, Alaaeldin and
Sharma, Shikhar and
Schulz, Hannes and
Hjelm, Devon and
El Asri, Layla and
Ebrahimi Kahou, Samira and
Bengio, Yoshua and
Taylor, Graham W.},
booktitle = {Neural Information Processing Systems (NIPS) Visually Grounded Interaction and Language (ViGIL) Workshop},
month = {December},
year = {2018},
url = {https://nips2018vigil.github.io/static/papers/accepted/13.pdf}
}