Light Field Synthesis from a Single Image using Improved Wasserstein Generative Adversarial Network
| dc.contributor.author | Ruan, Lingyan | en_US |
| dc.contributor.author | Chen, Bin | en_US |
| dc.contributor.author | Lam, Miu Ling | en_US |
| dc.contributor.editor | Jain, Eakta and Kosinka, Jirà | en_US |
| dc.date.accessioned | 2018-04-14T18:29:55Z | |
| dc.date.available | 2018-04-14T18:29:55Z | |
| dc.date.issued | 2018 | |
| dc.description.abstract | We present a deep learning-based method to synthesize a 4D light field from a single 2D RGB image. We consider the light field synthesis problem equivalent to image super-resolution, and solve it by using the improved Wasserstein Generative Adversarial Network with gradient penalty (WGAN-GP). Experimental results demonstrate that our algorithm can predict complex occlusions and relative depths in challenging scenes. The light fields synthesized by our method has much higher signal-to-noise ratio and structural similarity than the state-of-the-art approach. | en_US |
| dc.description.sectionheaders | Posters | |
| dc.description.seriesinformation | EG 2018 - Posters | |
| dc.identifier.doi | 10.2312/egp.20181017 | |
| dc.identifier.issn | 1017-4656 | |
| dc.identifier.pages | 19-20 | |
| dc.identifier.uri | https://doi.org/10.2312/egp.20181017 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/egp20181017 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.subject | Computing methodologies | |
| dc.subject | Machine learning | |
| dc.subject | Computational photography | |
| dc.title | Light Field Synthesis from a Single Image using Improved Wasserstein Generative Adversarial Network | en_US |