# A Multimodal Dialogue System for Conversational Image Editing

arXiv: https://arxiv.org/abs/2002.06484 · HTML: https://mlsanity.com/paper/2002.06484/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Feb 2020.

## Built on by (most cited first, 3 of 3)

- [ImgEdit: A Unified Image Editing Dataset and Benchmark](https://mlsanity.com/paper/2505.20275/) (2025)
- [CAISE: Conversational Agent for Image Search and Editing](https://mlsanity.com/paper/2202.11847/) (2022)
- [Tell Your Story: Task-Oriented Dialogs for Interactive Content Creation](https://mlsanity.com/paper/2211.03940/) (2022)

## Abstract (arXiv)

In this paper, we present a multimodal dialogue system for Conversational Image Editing. We formulate our multimodal dialogue system as a Partially Observed Markov Decision Process (POMDP) and trained it with Deep Q-Network (DQN) and a user simulator. Our evaluation shows that the DQN policy outperforms a rule-based baseline policy, achieving 90% success rate under high error rates. We also conducted a real user study and analyzed real user behavior.