Für eine korrekte Darstellung dieser Seite benötigen Sie einen XHTML-standardkonformen Browser, der die Darstellung von CSS-Dateien zulässt.

Progressive Refinement Imaging

Contact: 
Background: 

Markus Kluge1, Tim Weyrich2, Andreas Kolb1:
Progressive Refinement Imaging
Computer Graphics Forum (CGF), 2019
 

A sample result of our progressive refinement imaging pipeline applied to a data set (left) comprising one reference image that is refined using six additional images captured with six different cameras over the period of 10 years. Compared to prior work (middle), our method (right) successfully generates photometrically and geometrically consistent results in an online and memory-efficient fashion without global optimization.

Abstract: This paper presents a novel technique for progressive online integration of uncalibrated image sequences with substantial geometric and/or photometric discrepancies into a single, geometrically and photometrically consistent image. Our approach can handle large sets of images, acquired from a nearly planar or infinitely distant scene at different resolutions in object domain and under variable local or global illumination conditions. It allows for efficient user guidance as its progressive nature provides a valid and consistent reconstruction at any moment during the online refinement process. Our approach avoids global optimization techniques, as commonly used in the field of image refinement, and progressively incorporates new imagery into a dynamically extendable and memory-efficient Laplacian pyramid. Our image registration process includes a coarse homography and a local refinement stage using optical flow. Photometric consistency is achieved by retaining the photometric intensities given in a reference image, while it is being refined. Globally blurred imagery and local geometric inconsistencies due to, e.g. motion are detected and removed prior to image fusion. We demonstrate the quality and robustness of our approach using several image and video sequences, including handheld acquisition with mobile phones and zooming sequences with consumer cameras.

1 University of Siegen
2
University College London

Photo: "Herculaneum" by Johnboy Davidson is licensed under CC BY-NC 2.0
Paper: High-res (51 MB) / Low-res   Supplementary Material: High-res (272 MB) / Low-res
Input (reference image) vs. our result (refined reference image)
Publications: 


2020

Articles/Journal Papers

[bib] - Markus Kluge, Tim Weyrich, Andreas Kolb - Progressive Refinement Imaging
In Computer Graphics Forum (CGF), 39(1), 2020, pages 360-374 - [pdf]