Multi-scale Monocular Panorama Depth Estimation
| dc.contributor.author | Mohadikar, Payal | en_US |
| dc.contributor.author | Fan, Chuanmao | en_US |
| dc.contributor.author | Zhao, Chenxi | en_US |
| dc.contributor.author | Duan, Ye | en_US |
| dc.contributor.editor | Chaine, Raphaëlle | en_US |
| dc.contributor.editor | Deng, Zhigang | en_US |
| dc.contributor.editor | Kim, Min H. | en_US |
| dc.date.accessioned | 2023-10-09T07:42:54Z | |
| dc.date.available | 2023-10-09T07:42:54Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | Panorama images are widely used for scene depth estimation as they provide comprehensive scene representation. The existing deep-learning monocular panorama depth estimation networks produce inconsistent, discontinuous, and poor-quality depth maps. To overcome this, we propose a novel multi-scale monocular panorama depth estimation framework. We use a coarseto- fine depth estimation approach, where multi-scale tangent perspective images, projected from 360 images, are given to coarse and fine encoder-decoder networks to produce multi-scale perspective depth maps, that are merged to get low and high-resolution 360 depth maps. The coarse branch extracts holistic features that guide fine branch extracted features using a Multi-Scale Feature Fusion (MSFF) module at the network bottleneck. The performed experiments on the Stanford2D3D benchmark dataset show that our model outperforms the existing methods, producing consistent, smooth, structure-detailed, and accurate depth maps. | en_US |
| dc.description.sectionheaders | Posters | |
| dc.description.seriesinformation | Pacific Graphics Short Papers and Posters | |
| dc.identifier.doi | 10.2312/pg.20231282 | |
| dc.identifier.isbn | 978-3-03868-234-9 | |
| dc.identifier.pages | 113-114 | |
| dc.identifier.pages | 2 pages | |
| dc.identifier.uri | https://doi.org/10.2312/pg.20231282 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/pg20231282 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | CCS Concepts: Computing methodologies -> Scene understanding | |
| dc.subject | Computing methodologies | |
| dc.subject | Scene understanding | |
| dc.title | Multi-scale Monocular Panorama Depth Estimation | en_US |