Abstract
Bit-depth is the number of bits for each color channel of a pixel in an image. Although many modern displays support unprecedented higher bit-depth to show more realistic and natural colors with a high dynamic range, most media sources are still in bit-depth of 8 or lower. Since insufficient bit-depth may generate annoying false contours or lose detailed visual appearance, bit-depth expansion (BDE) from low bit-depth (LBD) images to high bit-depth (HBD) images becomes more and more important. In this paper, we adopt a learning-based approach for BDE and propose a novel CNN-based bit-depth expansion network (BitNet) that can effectively remove false contours and restore visual details at the same time. We have carefully designed our BitNet based on an encoder-decoder architecture with dilated convolutions and a novel multi-scale feature integration. We have performed various experiments with four different datasets including MIT-Adobe FiveK, Kodak, ESPL v2, and TESTIMAGES, and our proposed BitNet has achieved state-of-the-art performance in terms of PSNR and SSIM among other existing BDE methods and famous CNN-based image processing networks. Unlike previous methods that separately process each color channel, we treat all RGB channels at once and have greatly improved color restoration. In addition, our network has shown the fastest computational speed in near real-time.
J. Byun and K. Shim—Contributed equally, listed alphabetically.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https://www.tensorflow.org/. Software available from tensorflow.org
Asuni, N., Giachetti, A.: TESTIMAGES: a large-scale archive for testing visual devices and basic image processing algorithms. In: STAG - Smart Tools & Apps for Graphics Conference (2014). https://doi.org/10.2312/stag.20141242
Bychkovsky, V., Paris, S., Chan, E., Durand, F.: Learning photographic global tonal adjustment with a database of input/output image pairs. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2011
Chen, Q., Xu, J., Koltun, V.: Fast image processing with fully-convolutional networks. In: The IEEE International Conference on Computer Vision (ICCV), October 2017
Cheng, C.H., Au, O.C., Liu, C.H., Yip, K.Y.: Bit-depth expansion by contour region reconstruction. In: The IEEE International Symposium on Circuits and Systems, pp. 944–947, May 2009
Chollet, F., et al.: Keras (2015). https://keras.io
Daly, S., Feng, X.: Decontouring: Prevention and removal of false contour artifacts. In: The International Society for Optical Engineering (SPIE). vol. 5292, pp. 130–149 (2004)
Dong, C., Deng, Y., Loy, C.C., Tang, X.: Compression artifacts reduction by a deep convolutional network. In: The IEEE International Conference on Computer Vision (ICCV), pp. 576–584, December 2015
Dumoulin, V., Visin, F.: A guide to convolution arithmetic for deep learning (2016), arXiv preprint arXiv:1603.07285
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Teh, Y.W., Titterington, M. (eds.) Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research, vol. 9, pp. 249–256. PMLR, May 2010
Guo, J., Chao, H.: One-to-many network for visually pleasing compression artifacts reduction. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4867–4876, July 2017
Hall, C., Lowe, M.: Mobile HDR: Dolby vision, HDR10 and mobile HDR premium explained (2018). https://www.pocket-lint.com/phones/news/dolby/138387-mobile-hdr-dolby-vision-hdr10-and-mobile-hdr-premium-explained. Accessed 23 June 2018
Keysers, D., Lampert, C.H., Breuel, T.M.: Color image dequantization by constrained diffusion. In: The International Society for Optical Engineering (SPIE), vol. 6058, p. 6058-1–6058-10, January 2006
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR), May 2015
Kodak: Kodak lossless true color image suite (1999). http://r0k.us/graphics/kodak/. Accessed 23 June 2018
Kundu, D., Evans, B.L.: Full-reference visual quality assessment for synthetic images: a subjective study. In: The IEEE International Conference on Image Processing (ICIP), pp. 2374–2378, September 2015
Lefkimmiatis, S.: Universal denoising networks: a novel CNN architecture for image denoising. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018
Liu, C.H., Au, O.C., Wong, P.H.W., Kung, M.C., Chao, S.C.: Bit-depth expansion by adaptive filter. In: IEEE International Symposium on Circuits and Systems, pp. 496–499, May 2008
Liu, J., Zhai, G., Yang, X., Chen, C.W.: IPAD: intensity potential for adaptive de-quantization. IEEE Trans. Image Process. (2018)
Liu, S., Pan, J., Yang, M.-H.: Learning recursive filters for low-level vision via a hybrid neural network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 560–576. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_34
Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: ICML Workshop on Deep Learning for Audio, Speech and Language Processing (2013)
Mantiuk, R., Krawczyk, G., Myszkowski, K., Seidel, H.P.: Perception-motivated high dynamic range video encoding. Special Issue ACM Transa. Graph. (SIGGRAPH) 23, 733–741 (2004)
Mizuno, A., Ikebe, M.: Bit-depth expansion for noisy contour reduction in natural images. In: The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1671–1675, March 2016
Park, M.H., Lee, J.W., Park, R.H., Kim, J.S.: False contour reduction using neural networks and adaptive bi-directional smoothing. IEEE Trans. Consum. Electron. 56(2), 870–878 (2010)
Seetzen, H., et al.: High dynamic range display systems. Special Issue ACM Trans. Graph. (SIGGRAPH), 760–768 (2004)
Ulichney, R.A., Cheung, S.: Pixel bit-depth increase by bit replication. In: The International Society for Optical Engineering (SPIE), vol. 3300, pp. 3300-1–3300-10, January 1998
Wan, P., Au, O.C., Tang, K., Guo, Y., Fang, L.: From 2D extrapolation to 1D interpolation: content adaptive image bit-depth expansion. In: The IEEE International Conference on Multimedia and Expo (ICME), pp. 170–175, July 2012
Wan, P., Cheung, G., Florencio, D., Zhang, C., Au, O.C.: Image bit-depth enhancement via maximum a posteriori estimation of AC signal. IEEE Trans. Image Process. 25(6), 2896–2909 (2016)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Zhang, K., Zuo, W., Zhang, L.: FFDNET: toward a fast and flexible solution for cnn-based image denoising. IEEE Trans. Image Process. 27(9), 4608–4622 (2018)
Zhao, H., Gallo, O., Frosio, I., Kautz, J.: Loss functions for image restoration with neural networks. IEEE Trans. Comput. Imaging 3(1), 47–57 (2017)
Acknowledgement
This work was supported by MCST (Ministry of Culture, Sports & Tourism)/KOCCA (KoreaCreativeContentAgency) (R2016030044 - Development of Centext-Based Sports Video Analysis, Summarization, and Retrieval Technologies). The authors would like to thank Jing Liu [19] for releasing source codes for various BDE methods.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Byun, J., Shim, K., Kim, C. (2019). BitNet: Learning-Based Bit-Depth Expansion. In: Jawahar, C., Li, H., Mori, G., Schindler, K. (eds) Computer Vision – ACCV 2018. ACCV 2018. Lecture Notes in Computer Science(), vol 11362. Springer, Cham. https://doi.org/10.1007/978-3-030-20890-5_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-20890-5_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20889-9
Online ISBN: 978-3-030-20890-5
eBook Packages: Computer ScienceComputer Science (R0)