Lighting Spectral Power Distribution Estimation With RGB Camera

This paper explores the problem of the estimation of illumination spectral power distribution (SPD) derived both from sRGB images and a machine learning technique based on a vector-to-vector regression method. In order to overcome the lack of training SPD data, we have built a large sRGB image dataset along with the lighting SPD where the various unique illuminations were generated by an advanced 24-channel LED lighting system. The final dataset includes real data captured with a professional camera and synthesized data produced by a virtual camera model. The estimation results obtained clearly show consistent performance across a wide range of spectra.

[1]  Clayton D. Scott,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Esteban Walter Gonzalez Clua,et al.  Spatially and color consistent environment lighting estimation using deep neural networks for mixed reality , 2021, Comput. Graph..

[3]  Jean-Baptiste Thomas,et al.  Reflectance estimation from snapshot multispectral images captured under unknown illumination , 2021, Color and Imaging Conference.

[4]  W. Heidrich,et al.  Multispectral illumination estimation using deep unrolling network , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[5]  Sven Loncaric,et al.  The Cube++ Illumination Estimation Dataset , 2020, IEEE Access.

[6]  Masatoshi Okutomi,et al.  Spectral Reflectance Estimation Using Projector with Unknown Spectral Power Distribution , 2020, ArXiv.

[7]  D. Andrew Rowlands,et al.  Color conversion matrices in digital cameras: a tutorial , 2020 .

[8]  Michael S. Brown,et al.  Deep White-Balance Editing , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Michael S. Brown,et al.  Sensor-Independent Illumination Estimation for DNN Models , 2019, BMVC.

[10]  Onur Avci,et al.  1D Convolutional Neural Networks and Applications: A Survey , 2019, Mechanical Systems and Signal Processing.

[11]  Aleix Llenas,et al.  Arbitrary spectral matching using multi-LED lighting systems , 2019, Optical Engineering.

[12]  Antonio Robles-Kelly,et al.  A Convolutional Neural Network for Pixelwise Illuminant Recovery in Colour and Spectral Images , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[13]  Michael S. Brown,et al.  Improving Color Reproduction Accuracy on Cameras , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  Jon Yngve Hardeberg,et al.  Illuminant estimation in multispectral imaging. , 2017, Journal of the Optical Society of America. A, Optics, image science, and vision.

[15]  Yannick Hold-Geoffroy,et al.  Deep Outdoor Illumination Estimation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Dilip K Prasad,et al.  Illuminant estimation for color constancy: why spatial-domain methods work and the role of the color distribution. , 2014, Journal of the Optical Society of America. A, Optics, image science, and vision.

[17]  Sabine Süsstrunk,et al.  Optimum spectral sensitivity functions for single sensor color imaging , 2012, Electronic Imaging.

[18]  Carlos Ricolfe-Viala,et al.  Lens distortion models evaluation. , 2010, Applied optics.

[19]  Woo-Jin Song,et al.  Removing chromatic aberration by digital image processing , 2010 .

[20]  L. Macaire,et al.  Comparison of color demosaicing methods , 2010 .

[21]  Standard for Characterization of Image Sensors and Cameras Release 3 . 1 , 2010 .

[22]  Stephen Lin,et al.  Single-Image Vignetting Correction , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Javier Romero,et al.  Unsupervised illuminant estimation from natural scenes: an RGB digital camera suffices. , 2008, Applied optics.

[24]  Andrew Blake,et al.  Bayesian color constancy revisited , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Giancarlo Calvagno,et al.  Demosaicing With Directional Filtering and a posteriori Decision , 2007, IEEE Transactions on Image Processing.

[26]  Michael G. Madden,et al.  The effect of principal component analysis on machine learning accuracy with high-dimensional spectral data , 2005, Knowl. Based Syst..

[27]  Graham D. Finlayson,et al.  Shades of Gray and Colour Constancy , 2004, CIC.

[28]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[29]  Henrique S. Malvar,et al.  High-quality linear interpolation for demosaicing of Bayer-patterned color images , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[30]  Chein-I. Chang.  Spectral information divergence for hyperspectral image analysis , 1999, IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293).

[31]  Javier Hernández-Andrés,et al.  Linear bases for representation of natural and artificial illuminants , 1997 .

[32]  Matthew Anderson,et al.  Proposal for a Standard Default Color Space for the Internet - sRGB , 1996, CIC.

[33]  Fred A. Kruse,et al.  The Spectral Image Processing System (SIPS) - Interactive visualization and analysis of imaging spectrometer data , 1993 .

[34]  G. Smith,et al.  The spherical aberration of intra‐ocular lenses , 1988, Ophthalmic & physiological optics : the journal of the British College of Ophthalmic Opticians.