# Learning to Globally Edit Images with Textual Description

arXiv: https://arxiv.org/abs/1810.05786 · HTML: https://mlsanity.com/paper/1810.05786/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Oct 2018.

## Built on by (most cited first, 7 of 7)

- [Learning by Planning: Language-Guided Global Image Editing](https://mlsanity.com/paper/2106.13156/) (2021)
- [ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation](https://mlsanity.com/paper/2204.04428/) (2022)
- [Repositioning the Subject within Image](https://mlsanity.com/paper/2401.16861/) (2024)
- [Text-to-Image Cross-Modal Generation: A Systematic Review](https://mlsanity.com/paper/2401.11631/) (2024)
- [A Survey of Multimodal Composite Editing and Retrieval](https://mlsanity.com/paper/2409.05405/) (2024)
- [Entity-Level Text-Guided Image Manipulation](https://mlsanity.com/paper/2302.11383/) (2023)
- [SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Editing](https://mlsanity.com/paper/2112.00180/) (2021)

## Abstract (arXiv)

We show how we can globally edit images using textual instructions: given a source image and a textual instruction for the edit, generate a new image transformed under this instruction. To tackle this novel problem, we develop three different trainable models based on RNN and Generative Adversarial Network (GAN). The models (bucket, filter bank, and end-to-end) differ in how much expert knowledge is encoded, with the most general version being purely end-to-end. To train these systems, we use Amazon Mechanical Turk to collect textual descriptions for around 2000 image pairs sampled from several datasets. Experimental results evaluated on our dataset validate our approaches. In addition, given that the filter bank model is a good compromise between generality and performance, we investigate it further by replacing RNN with Graph RNN, and show that Graph RNN improves performance. To the best of our knowledge, this is the first computational photography work on global image editing that is purely based on free-form textual instructions.