Deep Specialized Network for Illuminant Estimation
نویسندگان
چکیده
Illuminant estimation to achieve color constancy is an illposed problem. Searching the large hypothesis space for an accurate illuminant estimation is hard due to the ambiguities of unknown reflections and local patch appearances. In this work, we propose a novel Deep Specialized Network (DS-Net) that is adaptive to diverse local regions for estimating robust local illuminants. This is achieved through a new convolutional network architecture with two interacting sub-networks, i.e. an hypotheses network (HypNet) and a selection network (SelNet). In particular, HypNet generates multiple illuminant hypotheses that inherently capture different modes of illuminants with its unique two-branch structure. SelNet then adaptively picks for confident estimations from these plausible hypotheses. Extensive experiments on the two largest color constancy benchmark datasets show that the proposed ‘hypothesis selection’ approach is effective to overcome erroneous estimation. Through the synergy of HypNet and SelNet, our approach outperforms state-of-the-art methods such as [1–3].
منابع مشابه
Approaching the computational color constancy as a classification problem through deep learning
Computational color constancy refers to the problem of computing the illuminant color so that the images of a scene under varying illumination can be normalized to an image under the canonical illumination. In this paper, we adopt a deep learning framework for the illumination estimation problem. The proposed method works under the assumption of uniform illumination over the scene and aims for ...
متن کاملNatural image database and its use for scene illuminant estimation
This paper describes a database collecting natural color images, called the Natural Image Database, and shows how it is used for illuminant estimation problems. First, we present significant features of the database. This database is not only a collection of color images of natural scenes, but also includes scene illuminant spectra and camera calibration data. Because these data sets are availa...
متن کاملReproduction Angular Error: An Improved Performance Metric for Illuminant Estimation
Only if we can estimate the colour of the prevailing light and discount it from the image can image colour be used as a stable cue for indexing, recognition and tracking (amongst other tasks). Almost all illumination estimation research uses the angle between the RGB of the actual measured illuminant colour and that estimated one as the recovery error. However here we identify a problem with th...
متن کاملColor by Correlation: A Simple, Unifying Framework for Color Constancy
ÐThis paper considers the problem of illuminant estimation: how, given an image of a scene, recorded under an unknown light, we can recover an estimate of that light. Obtaining such an estimate is a central part of solving the color constancy problemÐthat is of recovering an illuminant independent representation of the reflectances in a scene. Thus, the work presented here will have application...
متن کامل