TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Reverse Imaging Pipeline for Raw RGB Image Augmentation

Tutkimustuotosvertaisarvioitu

Standard

Reverse Imaging Pipeline for Raw RGB Image Augmentation. / Koskinen, Samu; Yang, Dang; Kämäräinen, Joni-Kristian.

2019 IEEE International Conference on Image Processing (ICIP). IEEE, 2019. s. 2896-2900 (IEEE International Conference on Image Processing).

Tutkimustuotosvertaisarvioitu

Harvard

Koskinen, S, Yang, D & Kämäräinen, J-K 2019, Reverse Imaging Pipeline for Raw RGB Image Augmentation. julkaisussa 2019 IEEE International Conference on Image Processing (ICIP). IEEE International Conference on Image Processing, IEEE, Sivut 2896-2900, IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 1/01/00. https://doi.org/10.1109/ICIP.2019.8804406

APA

Koskinen, S., Yang, D., & Kämäräinen, J-K. (2019). Reverse Imaging Pipeline for Raw RGB Image Augmentation. teoksessa 2019 IEEE International Conference on Image Processing (ICIP) (Sivut 2896-2900). (IEEE International Conference on Image Processing). IEEE. https://doi.org/10.1109/ICIP.2019.8804406

Vancouver

Koskinen S, Yang D, Kämäräinen J-K. Reverse Imaging Pipeline for Raw RGB Image Augmentation. julkaisussa 2019 IEEE International Conference on Image Processing (ICIP). IEEE. 2019. s. 2896-2900. (IEEE International Conference on Image Processing). https://doi.org/10.1109/ICIP.2019.8804406

Author

Koskinen, Samu ; Yang, Dang ; Kämäräinen, Joni-Kristian. / Reverse Imaging Pipeline for Raw RGB Image Augmentation. 2019 IEEE International Conference on Image Processing (ICIP). IEEE, 2019. Sivut 2896-2900 (IEEE International Conference on Image Processing).

Bibtex - Lataa

@inproceedings{c983a80072c74cf59d0da58ffe909a0a,
title = "Reverse Imaging Pipeline for Raw RGB Image Augmentation",
abstract = "We propose a reverse camera imaging pipeline to convert arbitrary images to raw RGB responses of a specific camera. The pipeline requires only that the camera’s RGB responses are characterized. The reversed pipeline helps camera developers to generate camera specific raw images and use them to train learning-based imaging pipeline algorithms. In our experiments, three recent deep color constancy architectures achieve superior results in the cross-dataset setting using generated images.",
keywords = "Image color analysis, Cameras, Pipelines, Pipeline processing, Lighting, Transforms, Data augmentation, imaging pipeline",
author = "Samu Koskinen and Dang Yang and Joni-Kristian K{\"a}m{\"a}r{\"a}inen",
note = "EXT={"}Koskinen, Samu{"}",
year = "2019",
month = "9",
doi = "10.1109/ICIP.2019.8804406",
language = "English",
isbn = "978-1-5386-6250-2",
series = "IEEE International Conference on Image Processing",
publisher = "IEEE",
pages = "2896--2900",
booktitle = "2019 IEEE International Conference on Image Processing (ICIP)",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Reverse Imaging Pipeline for Raw RGB Image Augmentation

AU - Koskinen, Samu

AU - Yang, Dang

AU - Kämäräinen, Joni-Kristian

N1 - EXT="Koskinen, Samu"

PY - 2019/9

Y1 - 2019/9

N2 - We propose a reverse camera imaging pipeline to convert arbitrary images to raw RGB responses of a specific camera. The pipeline requires only that the camera’s RGB responses are characterized. The reversed pipeline helps camera developers to generate camera specific raw images and use them to train learning-based imaging pipeline algorithms. In our experiments, three recent deep color constancy architectures achieve superior results in the cross-dataset setting using generated images.

AB - We propose a reverse camera imaging pipeline to convert arbitrary images to raw RGB responses of a specific camera. The pipeline requires only that the camera’s RGB responses are characterized. The reversed pipeline helps camera developers to generate camera specific raw images and use them to train learning-based imaging pipeline algorithms. In our experiments, three recent deep color constancy architectures achieve superior results in the cross-dataset setting using generated images.

KW - Image color analysis

KW - Cameras

KW - Pipelines

KW - Pipeline processing

KW - Lighting

KW - Transforms

KW - Data augmentation

KW - imaging pipeline

U2 - 10.1109/ICIP.2019.8804406

DO - 10.1109/ICIP.2019.8804406

M3 - Conference contribution

SN - 978-1-5386-6250-2

T3 - IEEE International Conference on Image Processing

SP - 2896

EP - 2900

BT - 2019 IEEE International Conference on Image Processing (ICIP)

PB - IEEE

ER -