Name
Abstract | ||
|---|---|---|
This paper investigates a novel problem of generating images from visual attributes. We model the image as a composite of foreground and background and develop a layered generative model with disentangled latent variables that can be learned end-to-end using a variational auto-encoder. We experiment with natural images of faces and birds and demonstrate that the proposed models are capable of generating realistic and diverse samples with disentangled latent representations. We use a general energy minimization algorithm for posterior inference of latent variables given novel images. Therefore, the learned generative models show excellent quantitative and visual results in the tasks of attribute-conditioned image reconstruction and completion. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1007/978-3-319-46493-0_47 | COMPUTER VISION - ECCV 2016, PT IV |
Keywords | Field | DocType |
Face Image,Image Generation,Convolutional Neural Network,Deep Neural Network,Recognition Model | Image generation,Bayesian inference,Computer science,Artificial intelligence,Rendering (computer graphics),Machine learning,Feature learning,Generative model | Journal |
Volume | ISSN | Citations |
9908 | 0302-9743 | 132 |
PageRank | References | Authors |
4.77 | 38 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xinchen Yan | 1 | 415 | 16.71 |
| Jimei Yang | 2 | 1083 | 40.68 |
| Kihyuk Sohn | 3 | 629 | 32.95 |
| Honglak Lee | 4 | 6247 | 398.39 |