Mapping colour in image stitching applications
Digitally, panoramic pictures can be assembled from several individual, overlapping photographs. While the geometric alignment of these photographs has retained a lot of attention from the computer vision community, the mapping of colour, i.e. the correction of colour mismatches, has not been studied extensively. In this article, we analyze the colour rendering of today’s digital photographic systems, and propose a method to correct for colour differences. The colour correction consists in retrieving linearized relative scene referred data from uncalibrated images by estimating the Opto-Electronic Conversion Function (OECF) and correcting for exposure, white-point, and vignetting variations between the individual pictures. Different OECF estimation methods are presented and evaluated in conjunction with motion estimation. The resulting panoramas, shown on examples using slides and digital photographs, yield much-improved visual quality compared to stitching using only motion estimation. Additionally, we show that colour correction can also improve the geometrical alignment.
Keywords: IVRG ; Digital panoramic photography ; scene-referred image encoding ; motion estimation ; pose estimation ; colour correction ; Laguerre OECF ; Polynomial OECF ; white-balancing ; mosaicing ; vignetting ; NCCR-MICS/CL4 ; NCCR-MICS
Record created on 2005-05-21, modified on 2016-08-08