Learning Scene Illumination by Pairwise Photos from Rear and Front Mobile Cameras
| dc.contributor.author | Cheng, Dachuan | en_US |
| dc.contributor.author | Shi, Jian | en_US |
| dc.contributor.author | Chen, Yanyun | en_US |
| dc.contributor.author | Deng, Xiaoming | en_US |
| dc.contributor.author | Zhang, Xiaopeng | en_US |
| dc.contributor.editor | Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes | en_US |
| dc.date.accessioned | 2018-10-07T14:59:17Z | |
| dc.date.available | 2018-10-07T14:59:17Z | |
| dc.date.issued | 2018 | |
| dc.description.abstract | Illumination estimation is an essential problem in computer vision, graphics and augmented reality. In this paper, we propose a learning based method to recover low-frequency scene illumination represented as spherical harmonic (SH) functions by pairwise photos from rear and front cameras on mobile devices. An end-to-end deep convolutional neural network (CNN) structure is designed to process images on symmetric views and predict SH coefficients. We introduce a novel Render Loss to improve the rendering quality of the predicted illumination. A high quality high dynamic range (HDR) panoramic image dataset was developed for training and evaluation. Experiments show that our model produces visually and quantitatively superior results compared to the state-of-the-arts. Moreover, our method is practical for mobile-based applications. | en_US |
| dc.description.number | 7 | |
| dc.description.sectionheaders | Appearance and Illumination | |
| dc.description.seriesinformation | Computer Graphics Forum | |
| dc.description.volume | 37 | |
| dc.identifier.doi | 10.1111/cgf.13561 | |
| dc.identifier.issn | 1467-8659 | |
| dc.identifier.pages | 213-221 | |
| dc.identifier.uri | https://doi.org/10.1111/cgf.13561 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.1111/cgf13561 | |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.subject | Human | |
| dc.subject | centered computing | |
| dc.subject | Mixed / augmented reality | |
| dc.subject | Computing methodologies | |
| dc.subject | Scene understanding | |
| dc.subject | Rendering | |
| dc.title | Learning Scene Illumination by Pairwise Photos from Rear and Front Mobile Cameras | en_US |