Abstract
A few methods have been proposed to estimate the CRF from a single image, however most of them tend to fail in handling general real images. For instance, EdgeCRF based on patches extracted from colour edges works effectively only when the presence of noise is insignificant, which is not the case for many real images; and, CRFNet, a recent method based on fully supervised deep learning works only for the CRFs that are in the training data, and hence fail to deal with other possible CRFs beyond the training data. To address these problems, we introduce a non-deep-learning method using prediction consistency and gradual refinement. First, we rely more on the patches of the input image that provide more consistent predictions. If the predictions from a patch are more consistent, it means that the patch is likely to be less affected by noise or any inferior colour combinations, and hence, it can be more reliable for CRF estimation. Second, we employ a gradual refinement scheme in which we start from a simple CRF model to generate a result which is more robust to noise but less accurate, and then we gradually increase the model’s complexity to improve the estimation. This is because a simple model, while being less accurate, overfits less to noise than a complex model does. Our experiments confirm that our method outperforms the existing single-image methods for both daytime and nighttime real images.
This work is supported by MOE2019-T2-1-130.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Kim, S.J., Frahm, J.M., Pollefeys, M.: Radiometric calibration with illumination change for outdoor scene analysis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2008)
Zhang, R., Tsai, P.S., Cryer, J.E., Shah, M.: Shape-from-shading: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 21, 690–706 (1999)
Nayar, S.K., Ikeuchi, K., Kanade, T.: Shape from interreflections. Int. J. Comput. Vis. 6, 173–195 (1991). https://doi.org/10.1007/BF00115695
Finlayson, G.D., Hordley, S.D., Hubel, P.M.: Color by correlation: a simple, unifying framework for color constancy. IEEE Trans. Pattern Anal. Mach. Intell. 23, 1209–1221 (2001)
Tan, R.T., Nishino, K., Ikeuchi, K.: Color constancy through inverse-intensity chromaticity space. JOSA A 21, 321–334 (2004)
Shi, B., Matsushita, Y., Wei, Y., Xu, C., Tan, P.: Self-calibrating photometric stereo. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2010)
Shi, B., Inose, K., Matsushita, Y., Tan, P., Yeung, S.K., Ikeuchi, K.: Photometric stereo using internet images. In: International Conference on 3D Vision (3DV) (2014)
Tan, R.T., Ikeuchi, K.: Separating reflection components of textured surfaces using a single image. IEEE Trans. Pattern Anal. Mach. Intell. 27, 178–193 (2005)
Finlayson, G.D., Drew, M.S., Lu, C.: Entropy minimization for shadow removal. Int. J. Comput. Vis. 85, 35–57 (2009). https://doi.org/10.1007/s11263-009-0243-z
Ying, Z., Li, G., Ren, Y., Wang, R., Wang, W.: A new low-light image enhancement algorithm using camera response model. In: IEEE International Conference on Computer Vision Workshops (ICCVW) (2017)
Debevec, P.E., Malik, J.: Recovering high dynamic range radiance maps from photographs. In: Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH), SIGGRAPH 1997 (1997)
Mitsunaga, T., Nayar, S.K.: Radiometric self calibration. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (1999)
Mann, S.: Comparametric equations with practical applications in quantigraphic image processing. IEEE Trans. Image Process. (TIP) 9, 1389–1406 (2000)
Matsushita, Y., Lin, S.: Radiometric calibration from noise distributions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2007)
Lin, S., Gu, J., Yamazaki, S., Shum, H.Y.: Radiometric calibration from a single image. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2004)
Lin, S., Zhang, L.: Determining the radiometric response function from a single grayscale image. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2005)
Li, H., Peers, P.: CRF-net: single image radiometric calibration using CNNs. In: European Conference on Visual Media Production (CVMP) (2017)
Ng, T.T., Chang, S.F., Tsui, M.P.: Using geometry invariants for camera response function estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2007)
Grossberg, M.D., Nayar, S.K.: Modeling the space of camera response functions. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 26, 1272–1282 (2004)
Lee, J.Y., Matsushita, Y., Shi, B., Kweon, I.S., Ikeuchi, K.: Radiometric calibration by rank minimization. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 35, 144–156 (2012)
Kim, S.J., Pollefeys, M.: Robust radiometric calibration and vignetting correction. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 30, 562–576 (2008)
Litvinov, A., Schechner, Y.Y.: Addressing radiometric nonidealities: a unified framework. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2005)
Mann, S., Mann, R.: Quantigraphic imaging: estimating the camera response and exposures from differently exposed images. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2001)
Park, J., Tai, Y.W., Sinha, S.N., So Kweon, I.: Efficient and robust color consistency for community photo collections. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Díaz, M., Sturm, P.: Radiometric calibration using photo collections. In: IEEE International Conference on Computational Photography (ICCP) (2011)
Li, C., Lin, S., Zhou, K., Ikeuchi, K.: Radiometric calibration from faces in images. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Kao, Y.L., Chen, Y.S., Ouhyoung, M.: Progressive-CRF-net: single image radiometric calibration using stacked CNNs. In: ACM SIGGRAPH 2018 Posters, pp. 1–2 (2018)
Kim, S.J., Lin, H.T., Lu, Z., Süsstrunk, S., Lin, S., Brown, M.S.: A new in-camera imaging model for color computer vision and its application. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 34, 2289–2302 (2012)
Cheng, D., Prasad, D.K., Brown, M.S.: Illuminant estimation for color constancy: why spatial-domain methods work and the role of the color distribution. J. Opt. Soc. Am. A: 31, 1049–1058 (2014)
Chen, C., Chen, Q., Xu, J., Koltun, V.: Learning to see in the dark. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Guo, X., Li, Y., Ling, H.: LIME: low-light image enhancement via illumination map estimation. IEEE Trans. Image Process. 26, 982–993 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Sharma, A., Tan, R.T., Cheong, LF. (2021). Single-Image Camera Response Function Using Prediction Consistency and Gradual Refinement. In: Ishikawa, H., Liu, CL., Pajdla, T., Shi, J. (eds) Computer Vision – ACCV 2020. ACCV 2020. Lecture Notes in Computer Science(), vol 12627. Springer, Cham. https://doi.org/10.1007/978-3-030-69544-6_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-69544-6_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-69543-9
Online ISBN: 978-3-030-69544-6
eBook Packages: Computer ScienceComputer Science (R0)