Semantics Disentangling for Text-To-Image Generation

Guojun Yin, Bin Liu, Lu Sheng, Nenghai Yu, Xiaogang Wang, Jing Shao; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 2327-2336


Synthesizing photo-realistic images from text descriptions is a challenging problem. Previous studies have shown remarkable progresses on visual quality of the generated images. In this paper, we consider semantics from the input text descriptions in helping render photo-realistic images. However, diverse linguistic expressions pose challenges in extracting consistent semantics even they depict the same thing. To this end, we propose a novel photo-realistic text-to-image generation model that implicitly disentangles semantics to both fulfill the high-level semantic consistency and low-level semantic diversity. To be specific, we design (1) a Siamese mechanism in the discriminator to learn consistent high-level semantics, and (2) a visual-semantic embedding strategy by semantic-conditioned batch normalization to find diverse low-level semantics. Extensive experiments and ablation studies on CUB and MS-COCO datasets demonstrate the superiority of the proposed method in comparison to state-of-the-art methods.

Related Material

author = {Yin, Guojun and Liu, Bin and Sheng, Lu and Yu, Nenghai and Wang, Xiaogang and Shao, Jing},
title = {Semantics Disentangling for Text-To-Image Generation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}