Illumination estimation challenge: The experience of the first 2 years

Abstract

Illumination estimation is the essential step of computational color constancy, one of the core parts of various image processing pipelines of modern digital cameras. Having an accurate and reliable illumination estimation is important for reducing the illumination influence on the image colors. To motivate the generation of new ideas and the development of new algorithms in this field, two challenges on illumination estimation were conducted. The main advantage of testing a method on a challenge over testing it on some of the known datasets is the fact that the ground‐truth illuminations for the challenge test images are unknown up until the results have been submitted, which prevents any potential hyperparameter tuning that may be biased. The First illumination estimation challenge (IEC#1) had only a single task, global illumination estimation. The second illumination estimation challenge (IEC#2) was enriched with two additional tracks that encompassed indoor and two‐illuminant illumination estimation. Other main features of it are a new large dataset of images (about 5000) taken with the same camera sensor model, a manual markup accompanying each image, diverse content with scenes taken in numerous countries under a huge variety of illuminations extracted by using the SpyderCube calibration object, and a contest‐like markup for the images from the Cube++ dataset. This article focuses on the description of the past two challenges, algorithms which won in each track, and the conclusions that were drawn based on the results obtained during the first and second challenge that can be useful for similar future developments.

ReCC-GAN: scene global illuminant estimation network based on Retinex and generative adversarial network

“…However, minor errors are often imperceptible. 53 Therefore, the approach in this paper achieving the best results in the Worst25% indicator on any dataset is meaningful.…”

“…The primary objective of camera manufacturers is to minimize significant errors, assuming that a substantially incorrect white balance is undesirable for both photographers and viewers. However, minor errors are often imperceptible 53 . Therefore, the approach in this paper achieving the best results in the Worst25% indicator on any dataset is meaningful.…”

Segmentation of Agricultural Parcels in Satellite Images Based on Historical Vegetation Index Data

“…Much attention is being paid to the color properties of images. Physical approach-based color segmentation methods are being proposed [31,32], methods for use in evaluating the spectral characteristics of lighting sources are being developed [33] and the properties of color coordinate systems are being investigated [34], as well as the properties of color images registered in dense medium such as water [35]. With regard to working with multispectral images, methods for use in their visualization [36], restoration [37,38], and correction [29] are being actively developed.…”

Image understanding for color constancy and vice versa

“…At the beginning color constancy was commonly used as a pre-processing step to help improving the performance of image understanding tasks. More recently instead, color constancy has started to exploit the successful results obtained in image understanding and computer vision in general to create more robust color constancy algorithms, as is it also evident from the trends of the methods that participated in very recent illuminant estimation challenges [18].…”