Text to Image Generation with Semantic-Spatial Aware GAN
This addresses a specific limitation in text-to-image generation for applications requiring detailed semantic consistency, though it is incremental as it builds on existing GAN-based methods.
The paper tackles the problem of text-to-image synthesis where generated images often have regions inconsistent with specific words, such as 'a white crown', by proposing a Semantic-Spatial Aware GAN that learns semantic-adaptive transformations and masks to improve alignment. Experiments on COCO and CUB datasets show advantages over state-of-the-art methods in visual fidelity and text alignment.
Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions. Existing methods are usually built upon conditional generative adversarial networks (GANs) and initialize an image from noise with sentence embedding, and then refine the features with fine-grained word embedding iteratively. A close inspection of their generated images reveals a major limitation: even though the generated image holistically matches the description, individual image regions or parts of somethings are often not recognizable or consistent with words in the sentence, e.g. "a white crown". To address this problem, we propose a novel framework Semantic-Spatial Aware GAN for synthesizing images from input text. Concretely, we introduce a simple and effective Semantic-Spatial Aware block, which (1) learns semantic-adaptive transformation conditioned on text to effectively fuse text features and image features, and (2) learns a semantic mask in a weakly-supervised way that depends on the current text-image fusion process in order to guide the transformation spatially. Experiments on the challenging COCO and CUB bird datasets demonstrate the advantage of our method over the recent state-of-the-art approaches, regarding both visual fidelity and alignment with input text description.