Consistent Multi- and Single-View HDR-Image Reconstruction from Single Exposures
| dc.contributor.author | Mohan, Aditya | en_US |
| dc.contributor.author | Zhang, Jing | en_US |
| dc.contributor.author | Cozot, Remi | en_US |
| dc.contributor.author | Loscos, Celine | en_US |
| dc.contributor.editor | Ronfard, Rémi | en_US |
| dc.contributor.editor | Wu, Hui-Yin | en_US |
| dc.date.accessioned | 2022-04-20T08:33:42Z | |
| dc.date.available | 2022-04-20T08:33:42Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract | Recently, there have been attempts to obtain high-dynamic range (HDR) images from single exposures and efforts to reconstruct multi-view HDR images using multiple input exposures. However, there have not been any attempts to reconstruct multi-view HDR images from multi-view Single Exposures to the best of our knowledge. We present a two-step methodology to obtain color consistent multi-view HDR reconstructions from single-exposure multi-view low-dynamic-range (LDR) Images. We define a new combination of the Mean Absolute Error and Multi-Scale Structural Similarity Index loss functions to train a network to reconstruct an HDR image from an LDR one. Once trained we use this network to multi-view input. When tested on single images, the outputs achieve competitive results with the state-of-the-art. Quantitative and qualitative metrics applied to our results and to the state-of-the-art show that our HDR expansion is better than others while maintaining similar qualitative reconstruction results. We also demonstrate that applying this network on multi-view images ensures coherence throughout the generated grid of HDR images. | en_US |
| dc.description.sectionheaders | Intelligent and Virtual Cinematography | |
| dc.description.seriesinformation | Workshop on Intelligent Cinematography and Editing | |
| dc.identifier.doi | 10.2312/wiced.20221050 | |
| dc.identifier.isbn | 978-3-03868-173-1 | |
| dc.identifier.issn | 2411-9733 | |
| dc.identifier.pages | 37-44 | |
| dc.identifier.pages | 8 pages | |
| dc.identifier.uri | https://doi.org/10.2312/wiced.20221050 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/wiced20221050 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.subject | CCS Concepts: Computing methodologies --> Computational photography; Machine learning; 3D imaging | |
| dc.subject | Computing methodologies | |
| dc.subject | Computational photography | |
| dc.subject | Machine learning | |
| dc.subject | 3D imaging | |
| dc.title | Consistent Multi- and Single-View HDR-Image Reconstruction from Single Exposures | en_US |
Files
Original bundle
1 - 1 of 1