Disentangled Person Image Generation
Citations Over TimeTop 1% of 2018 papers
Abstract
Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information. In this work, we aim at generating such images based on a novel, two-stage reconstruction pipeline that learns a disentangled representation of the aforementioned image factors and generates novel person images at the same time. First, a multi-branched reconstruction network is proposed to disentangle and encode the three factors into embedding features, which are then combined to re-compose the input image itself. Second, three corresponding mapping functions are learned in an adversarial manner in order to map Gaussian noise to the learned embedding feature space, for each factor, respectively. Using the proposed framework, we can manipulate the foreground, background and pose of the input image, and also sample new embedding features to generate such targeted manipulations, that provide more control over the generation process. Experiments on the Market-1501 and Deepfashion datasets show that our model does not only generate realistic person images with new foregrounds, backgrounds and poses, but also manipulates the generated factors and interpolates the in-between states. Another set of experiments on Market-1501 shows that our model can also be beneficial for the person re-identification task 1 .
Related Papers
- → New developments on the Encyclopedia of DNA Elements (ENCODE) data portal(2019)1,073 cited
- → Using the ENCODE Resource for Functional Annotation of Genetic Variants(2015)32 cited
- → Extrapolating ENCODE data to the whole human genome(2008)2 cited
- The Study of OCDMA Encode/Decode Using Multilayer Films(2001)
- The ENCODE Project Decoded(2012)