Controllable Text-to-Image Generation

In this paper, we propose a novel controllable text-to-image generative adversarial network (ControlGAN), which can effectively synthesise high-quality images and also control parts of the image generation according to natural language descriptions. To achieve this, we introduce a word-level spatial and channel-wise attention-driven generator that can disentangle different visual attributes, and allow the model to focus on generating and manipulating subregions corresponding to the most relevant words. Also, a word-level discriminator is proposed to provide fine-grained supervisory feedback by correlating words with image regions, facilitating training an effective generator which is able to manipulate specific visual attributes without affecting the generation of other content. Furthermore, perceptual loss is adopted to reduce the randomness involved in the image generation, and to encourage the generator to manipulate specific attributes required in the modified text. Extensive experiments on benchmark datasets demonstrate that our method outperforms existing state of the art, and is able to effectively manipulate synthetic images using natural language descriptions. Code is available at https://github.com/mrlibw/ControlGAN.

PDF Abstract NeurIPS 2019 PDF NeurIPS 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Text-to-Image Generation COCO Attention-driven Generator (perceptual loss) Inception score 24.06 # 14
Text-to-Image Generation CUB Attention-driven Generator (perceptual loss) Inception score 4.58 # 5
Text-to-Image Generation Multi-Modal-CelebA-HQ ControlGAN FID 116.32 # 4
LPIPS 0.522 # 4
Acc 14.6 # 5
Real 13.1 # 5

Methods


No methods listed for this paper. Add relevant methods here