Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks
This work addresses the problem of generating realistic edited images from text descriptions for applications in computer vision and graphics, representing an incremental improvement over existing LBIE techniques.
The paper tackled the challenge of disentangling and combining semantics in images and text for Language-Based Image Editing (LBIE) by proposing a Bilinear Residual Layer (BRL) in conditional GANs, resulting in higher-quality generated images compared to previous methods.
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.