# Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1903.07499 · HTML: https://mlsanity.com/paper/1903.07499/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Mar 2019.

## Built on by (most cited first, 8 of 8)

- [More Control for Free! Image Synthesis with Semantic Diffusion Guidance](https://mlsanity.com/paper/2112.05744/) (2021)
- [Learning by Planning: Language-Guided Global Image Editing](https://mlsanity.com/paper/2106.13156/) (2021)
- [Text2Poster: Laying out Stylized Texts on Retrieved Images](https://mlsanity.com/paper/2301.02363/) (2023)
- [A Survey of Multimodal Composite Editing and Retrieval](https://mlsanity.com/paper/2409.05405/) (2024)
- [SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Editing](https://mlsanity.com/paper/2112.00180/) (2021)
- [TAI-GAN: A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correction](https://mlsanity.com/paper/2402.09567/) (2024)
- [TAI-GAN: Temporally and Anatomically Informed GAN for early-to-late frame conversion in dynamic cardiac PET motion correction](https://mlsanity.com/paper/2308.12443/) (2023)
- [Brownian Bridge Diffusion-Based Joint Channel Estimation and Data Detection for Jamming-Resilient Receivers](https://mlsanity.com/paper/2606.28778/) (2026)

## Abstract (arXiv)

The task of Language-Based Image Editing (LBIE) aims at generating a target image by editing the source image based on the given language description. The main challenge of LBIE is to disentangle the semantics in image and text and then combine them to generate realistic images. Therefore, the editing performance is heavily dependent on the learned representation. In this work, conditional generative adversarial network (cGAN) is utilized for LBIE. We find that existing conditioning methods in cGAN lack of representation power as they cannot learn the second-order correlation between two conditioning vectors. To solve this problem, we propose an improved conditional layer named Bilinear Residual Layer (BRL) to learning more powerful representations for LBIE task. Qualitative and quantitative comparisons demonstrate that our method can generate images with higher quality when compared to previous LBIE techniques.