Text Guided Person Image Synthesis
arXiv:1904.05118
Abstract
This paper presents a novel method to manipulate the visual appearance (pose and attribute) of a person image according to natural language descriptions. Our method can be boiled down to two stages: 1) text guided pose generation and 2) visual appearance transferred image synthesis. In the first stage, our method infers a reasonable target human pose based on the text. In the second stage, our method synthesizes a realistic and appearance transferred person image according to the text in conjunction with the target pose. Our method extracts sufficient information from the text and establishes a mapping between the image space and the language space, making generating and editing images corresponding to the description possible. We conduct extensive experiments to reveal the effectiveness of our method, as well as using the VQA Perceptual Score as a metric for evaluating the method. It shows for the first time that we can automatically edit the person image from the natural language descriptions.
To appear at CVPR 2019
References in corpus (9)
- Generative Adversarial Text to Image Synthesis
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Conditional Image Generation with PixelCNN Decoders
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Learning What and Where to Draw
- Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering
- Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
- Person Re-identification Meets Image Search
- Pose-Normalized Image Generation for Person Re-identification