arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1712.00436cs.CV
收藏

颜色恒常性的无监督学习

Unsupervised Learning for Color Constancy

University of Zagreb(萨格勒布大学)

Nikola Banić, Karlo Koščević, Sven Lončarić

摘要:

大多数数码相机流水线使用颜色恒常性方法来减少照明和相机传感器对场景对象颜色的影响。基于学习的颜色恒常性方法可以获得最高的颜色校正精度,但它们需要大量具有已知地面真实光照的校准训练图像。这种校准是耗时的,优选地针对每个传感器单独进行,并且因此是获取高颜色恒定性准确度的主要瓶颈。基于统计的方法不需要校准的训练图像,但它们不太准确。本文提出了一种基于无监督学习的方法,该方法在近似训练图像的未知地面真实光照之后学习其参数值,从而避免校准。在准确性方面,该方法优于所有基于几何学和许多基于学习的方法。还提出了一种扩展的方法,它学习所需的参数,从非校准的图像与一个传感器,然后可以成功地应用到与另一个传感器拍摄的图像。这有效地实现了用于颜色恒定性的相机间无监督学习。此外,还创建了一个新的高质量颜色恒定性基准数据集,其中包含1707个校准图像,用于测试,并公开提供。结果进行了介绍和讨论。源代码和数据集可在http://www.fer.unizg.hr/ipg/resources/color_constancy/上获得。

英文摘要:

Most digital camera pipelines use color constancy methods to reduce the influence of illumination and camera sensor on the colors of scene objects. The highest accuracy of color correction is obtained with learning-based color constancy methods, but they require a significant amount of calibrated training images with known ground-truth illumination. Such calibration is time consuming, preferably done for each sensor individually, and therefore a major bottleneck in acquiring high color constancy accuracy. Statistics-based methods do not require calibrated training images, but they are less accurate. In this paper an unsupervised learning-based method is proposed that learns its parameter values after approximating the unknown ground-truth illumination of the training images, thus avoiding calibration. In terms of accuracy the proposed method outperforms all statistics-based and many learning-based methods. An extension of the method is also proposed, which learns the needed parameters from non-calibrated images taken with one sensor and which can then be successfully applied to images taken with another sensor. This effectively enables inter-camera unsupervised learning for color constancy. Additionally, a new high quality color constancy benchmark dataset with 1707 calibrated images is created, used for testing, and made publicly available. The results are presented and discussed. The source code and the dataset are available at http://www.fer.unizg.hr/ipg/resources/color_constancy/.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑