Abstract | ||
---|---|---|
In this paper, we treat the image generation task using an autoencoder, a representative latent model. Unlike many studies regularizing the latent variable's distribution by assuming a manually specified prior, we approach the image generation task using an autoencoder by directly estimating the latent distribution. To this end, we introduce 'latent density estimator' which captures latent distribution explicitly and propose its structure. Through experiments, we show that our generative model generates images with the improved visual quality compared to previous autoencoder-based generative models. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/ICIP40778.2020.9191173 | 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) |
Keywords | DocType | ISSN |
Autoencoder, Image Generation, Generative Model, Density Estimation, Mixture Model | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jaeyoung Yoo | 1 | 0 | 0.34 |
Hojun Lee | 2 | 0 | 0.68 |
Nojun Kwak | 3 | 862 | 63.79 |