Name
Abstract | ||
|---|---|---|
Camera images saved in raw format are being adopted in computer vision tasks since raw values represent minimally processed sensor responses. Camera manufacturers, however, have yet to adopt a standard for raw images and current raw-rgb values are device specific due to different sensors spectral sensitivities. This results in significantly different raw images for the same scene captured with different cameras. This paper focuses on estimating a mapping that can convert a raw image of an arbitrary scene and illumination from one camera's raw space to another. To this end, we examine various mapping strategies including linear and non-linear transformations applied both in a global and illumination-specific manner. We show that illumination-specific mappings give the best result, however, at the expense of requiring a large number of transformations. To address this issue, we introduce an illumination-independent mapping approach that uses white-balancing to assist in reducing the number of required transformations. We show that this approach achieves state-of-the-art results on a range of consumer cameras and images of arbitrary scenes and illuminations. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/CVPR.2014.434 | Computer Vision and Pattern Recognition |
Keywords | Field | DocType |
cameras,computer vision,image colour analysis,image sensors,lighting,arbitrary illumination,arbitrary scene,camera images,camera manufacturers,computer vision tasks,global illumination-specific manner,illumination-independent mapping,image sensor color responses,linear transformations,minimally processed sensor responses,nonlinear transformations,raw format,raw images,raw-rgb values,raw-to-raw mapping estimation,sensors spectral sensitivity,transformation number reduction,white-balancing,raw to raw | Computer vision,Image sensor,Computer graphics (images),Computer science,Artificial intelligence | Conference |
ISSN | Citations | PageRank |
1063-6919 | 5 | 0.43 |
References | Authors | |
11 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Nguyen Ho Man Rang | 1 | 8 | 0.82 |
| Dilip K. Prasad | 2 | 162 | 21.84 |
| Michael S. Brown | 3 | 2122 | 129.13 |