Text to Image Synthesis using Stacked Conditional Variational Autoencoders and Conditional Generative Adversarial Networks
This work addresses the problem of text-to-image synthesis for computer vision applications, representing an incremental improvement over existing methods like StackGAN.
The paper tackles the challenge of generating high-resolution images from text descriptions by proposing a stacked Conditional VAE and Conditional GAN architecture, which yields competitive results on CUB and Oxford-102 datasets with scores based on Inception and Frechet Inception metrics.
Synthesizing a realistic image from textual description is a major challenge in computer vision. Current text to image synthesis approaches falls short of producing a highresolution image that represent a text descriptor. Most existing studies rely either on Generative Adversarial Networks (GANs) or Variational Auto Encoders (VAEs). GANs has the capability to produce sharper images but lacks the diversity of outputs, whereas VAEs are good at producing a diverse range of outputs, but the images generated are often blurred. Taking into account the relative advantages of both GANs and VAEs, we proposed a new stacked Conditional VAE (CVAE) and Conditional GAN (CGAN) network architecture for synthesizing images conditioned on a text description. This study uses Conditional VAEs as an initial generator to produce a high-level sketch of the text descriptor. This high-level sketch output from first stage and a text descriptor is used as an input to the conditional GAN network. The second stage GAN produces a 256x256 high resolution image. The proposed architecture benefits from a conditioning augmentation and a residual block on the Conditional GAN network to achieve the results. Multiple experiments were conducted using CUB and Oxford-102 dataset and the result of the proposed approach is compared against state-ofthe-art techniques such as StackGAN. The experiments illustrate that the proposed method generates a high-resolution image conditioned on text descriptions and yield competitive results based on Inception and Frechet Inception Score using both datasets