Reverse Imaging Pipeline for Raw RGB Image Augmentation

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Koskinen, Samu, Yang, Dan, Kamarainen, Joni-Kristian
Format: Conference Proceeding
Language:English
Subjects:
Cameras
Data augmentation
Image color analysis
imaging pipeline
Lighting
Pipeline processing
Pipelines
Transforms
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2381-8549
DOI:10.1109/ICIP.2019.8804406