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

03/18/2019
by   Xiaofeng Mao, et al.
0

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.

READ FULL TEXT
research
12/16/2019

Image Manipulation with Natural Language using Two-sidedAttentive Conditional Generative Adversarial Network

Altering the content of an image with photo editing tools is a tedious t...
research
11/16/2017

Language-Based Image Editing with Recurrent Attentive Models

We investigate the problem of Language-Based Image Editing (LBIE) in thi...
research
11/04/2016

Ways of Conditioning Generative Adversarial Networks

The GANs are generative models whose random samples realistically reflec...
research
05/14/2020

Enhanced Residual Networks for Context-based Image Outpainting

Although humans perform well at predicting what exists beyond the bounda...
research
08/19/2019

Boundless: Generative Adversarial Networks for Image Extension

Image extension models have broad applications in image editing, computa...
research
10/21/2021

Each Attribute Matters: Contrastive Attention for Sentence-based Image Editing

Sentence-based Image Editing (SIE) aims to deploy natural language to ed...
research
10/12/2021

Real Image Inversion via Segments

In this short report, we present a simple, yet effective approach to edi...

Please sign up or login with your details

Forgot password? Click here to reset