MetaISP -- Exploiting Global Scene Structure for Accurate Multi-Device Color Rendition
| dc.contributor.author | Souza, Matheus | en_US |
| dc.contributor.author | Heidrich, Wolfgang | en_US |
| dc.contributor.editor | Guthe, Michael | en_US |
| dc.contributor.editor | Grosch, Thorsten | en_US |
| dc.date.accessioned | 2023-09-25T11:38:40Z | |
| dc.date.available | 2023-09-25T11:38:40Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | Image signal processors (ISPs) are historically grown legacy software systems for reconstructing color images from noisy raw sensor measurements. Each smartphone manufacturer has developed its ISPs with its own characteristic heuristics for improving the color rendition, for example, skin tones and other visually essential colors. The recent interest in replacing the historically grown ISP systems with deep-learned pipelines to match DSLR's image quality improves structural features in the image. However, these works ignore the superior color processing based on semantic scene analysis that distinguishes mobile phone ISPs from DSLRs. Here we present MetaISP, a single model designed to learn how to translate between the color and local contrast characteristics of different devices. MetaISP takes the RAW image from device A as input and translates it to RGB images that inherit the appearance characteristics of devices A, B, and C. We achieve this result by employing a lightweight deep learning technique that conditions its output appearance based on the device of interest. In this approach, we leverage novel attention mechanisms inspired by cross-covariance learn global scene semantics. Additionally, we make use of metadata that typically accompanies raw images, and we estimate scene illuminants when they are not available. | en_US |
| dc.description.sectionheaders | Image Processing | |
| dc.description.seriesinformation | Vision, Modeling, and Visualization | |
| dc.identifier.doi | 10.2312/vmv.20231236 | |
| dc.identifier.isbn | 978-3-03868-232-5 | |
| dc.identifier.pages | 141-148 | |
| dc.identifier.pages | 8 pages | |
| dc.identifier.uri | https://doi.org/10.2312/vmv.20231236 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/vmv20231236 | |
| 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 -> Image Manipulation; Computational Photography | |
| dc.subject | Computing methodologies | |
| dc.subject | Image Manipulation | |
| dc.subject | Computational Photography | |
| dc.title | MetaISP -- Exploiting Global Scene Structure for Accurate Multi-Device Color Rendition | en_US |