Abstract | ||
---|---|---|
Generating images via the generative adversarial network (GAN) has attracted much attention recently. However, most of the existing GAN-based methods can only produce low-resolution images of limited quality. Directly generating high-resolution images using GANs is nontrivial, and often produces problematic images with incomplete objects. To address this issue, we develop a novel GAN called Auto-Embedding Generative Adversarial Network (AEGAN), which simultaneously encodes the global structure features and captures the fine-grained details. In our network, we use an autoencoder to learn the intrinsic high-level structure of real images and design a novel denoiser network to provide photo-realistic details for the generated images. In the experiments, we are able to produce 512x512 images of promising quality directly from the input noise. The resultant images exhibit better perceptual photo-realism, i.e., with sharper structure and richer details, than other baselines on several datasets, including Oxford-102 Flowers, Caltech-UCSD Birds (CUB), High-Quality Large-scale CelebFaces Attributes (CelebA-HQ), Large-scale Scene Understanding (LSUN) and ImageNet. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/tmm.2019.2908352 | IEEE Trans. Multimedia |
Keywords | Field | DocType |
Image resolution,Generative adversarial networks,Gallium nitride,Training,Data mining,Feature extraction,Generators | Computer vision,Embedding,Autoencoder,Pattern recognition,Computer science,Image synthesis,Feature extraction,Artificial intelligence,Real image,Generative grammar,Image resolution,Adversarial system | Journal |
Volume | Issue | ISSN |
abs/1903.11250 | 11 | 1520-9210 |
Citations | PageRank | References |
6 | 0.41 | 0 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yong Guo | 1 | 45 | 5.94 |
Qi Chen | 2 | 18 | 3.24 |
Jian Chen | 3 | 42 | 8.66 |
Wu Qingyao | 4 | 259 | 33.46 |
Qinfeng Shi | 5 | 1564 | 74.85 |
Rui Tang | 6 | 188 | 19.22 |