Abstract
Grayscale image colorization is an important computer graphics problem with a variety of applications. Recent fully automatic colorization methods have made impressive progress by formulating image colorization as a pixel-wise prediction task and utilizing deep convolutional neural networks. Though tremendous improvements have been made, the result of automatic colorization is still far from perfect. Specifically, there still exist common pitfalls in maintaining color consistency in homogeneous regions as well as precisely distinguishing colors near region boundaries. To tackle these problems, we propose a novel fully automatic colorization pipeline which involves a boundary-guided CRF (conditional random field) and a CNN-based color transform as post-processing steps. In addition, as there usually exist multiple plausible colorization proposals for a single image, automatic evaluation for different colorization methods remains a challenging task. We further introduce two novel automatic evaluation schemes to efficiently assess colorization quality in terms of spatial coherence and localization. Comprehensive experiments demonstrate great quality improvement in results of our proposed colorization method under multiple evaluation metrics.
Similar content being viewed by others
References
Levin A, Lischinski D, Weiss Y. Colorization using optimization. ACM Transactions on Graphics (TOG), 2004, 23(3): 689-694.
Huang Y C, Tung Y S, Chen J C, Wang S W, Wu J L. An adaptive edge detection based colorization algorithm and its applications. In Proc. the 13th Annual ACM International Conference on Multimedia, Nov. 2005, pp.351-354.
Luan Q, Wen F, Cohen-Or D, Liang L, Xu Y Q, Shum H Y. Natural image colorization. In Proc. the 18th Eurographics Conference on Rendering Techniques, Jun. 2007, pp.309-320.
Qu Y,Wong T T, Heng P A. Manga colorization. ACM Transactions on Graphics (TOG), 2006, 25(3): 1214-1220.
Zhao H L, Nie G Z, Li X J, Jin X G, Pan Z G. Structureaware nonlocal optimization framework for image colorization. Journal of Computer Science and Technology, 2015, 30(3): 478-488.
Sheng B, Sun H, Magnor M, Li P. Video colorization using parallel optimization in feature space. IEEE Transactions on Circuits and Systems for Video Technology, 2014, 24(3): 407-417.
Welsh T, Ashikhmin M, Mueller K. Transferring color to greyscale images. ACM Transactions on Graphics (TOG), 2002, 21(3): 277-280.
Irony R, Cohen-Or D, Lischinski D. Colorization by example. In Proc. Eurographics Symp. Rendering Techqiques, June 29-July 1, 2005, pp.201-210.
Charpiat G, Hofmann M, Sch¨olkopf B. Automatic image colorization via multimodal predictions. In Proc. the 10th European Conference on Computer Vision, Oct. 2008, pp.126-139.
Liu X, Wan L, Qu Y, Wong T T, Lin S, Leung C S, Heng P A. Intrinsic colorization. ACM Transactions on Graphics (TOG), 2008, 27(5): 152:1-152:9.
Gupta R K, Chia A Y S, Rajan D, Ng E S et al. Image colorization using similar images. In Proc. the 20th ACM International Conference on Multimedia, Oct.29-Nov.2, 2012, pp.369-378.
Jin S Y, Choi H J, Tai Y W. A randomized algorithm for natural object colorization. Computer Graphics Forum, 2014, 33(2): 205-214.
Chia A Y S, Zhuo S, Gupta R K, Tai Y W, Cho S Y, Tan P, Lin S. Semantic colorization with Internet images. ACM Transactions on Graphics (TOG), 2011, 30(6): 156:1-156:8.
Deshpande A, Rock J, Forsyth D. Learning large-scale automatic image colorization. In Proc. the IEEE International Conference on Computer Vision, Dec. 2015, pp.567-575.
Li X, Zhao H, Nie G, Huang H. Image recoloring using geodesic distance based color harmonization. Computational Visual Media, 2015, 1(2): 143-155.
Cheng Z, Yang Q, Sheng B. Deep colorization. In Proc. the IEEE International Conference on Computer Vision, Dec. 2015, pp.415-423.
Dahl R. Automatic colorization. http://tinyclouds.org/colorize/, Aug. 2016.
Larsson G, Maire M, Shakhnarovich G. Learning representations for automatic colorization. In Proc. European Conference on Computer Vision, Oct. 2016, pp.577-593.
Zhang R, Isola P, Efros A A. Colorful image colorization. In Proc. European Conference on Computer Vision, Oct. 2016, pp.649-666.
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556, 2014. https://arxiv.org/abs/1409.1556, Aug. 2016.
Hariharan B, Arbeláez P, Girshick R, Malik J. Hypercolumns for object segmentation and fine-grained localization. In Proc. the IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2015, pp.447-456.
Noh H, Hong S, Han B. Learning deconvolution network for semantic segmentation. In Proc. the IEEE International Conference on Computer Vision, Dec. 2015, pp.1520-1528.
Li G, Yu Y. Deep contrast learning for salient object detection. In Proc. the IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2016, pp.478-487.
Li G, Yu Y. Visual saliency based on multiscale deep features. In Proc. the IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2015, pp.5455-5463.
Ren S, He K, Girshick R, Sun J. Faster R-CNN: Towards real-time object detection with region proposal networks. In Proc. Advances in Neural Information Processing Systems, Dec. 2015, pp.91-99.
Xie S, Tu Z. Holistically-nested edge detection. In Proc. the IEEE International Conference on Computer Vision, Dec. 2015, pp.1395-1403.
Iizuka S, Simo-Serra E, Ishikawa H. Let there be color!: Joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification. ACM Transactions on Graphics (TOG), 2016, 35(4): 110:1-110:11.
Noh H, Hong S, Han B. Learning deconvolution network for semantic segmentation. In Proc. the IEEE International Conference on Computer Vision, Dec. 2015, pp.1520-1528.
Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122, 2015. https://arxiv.org/abs/1511.07122, Aug. 2016.
Boykov Y, Veksler O, Zabih R. Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(11): 1222-1239.
He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proc. the IEEE International Conference on Computer Vision, Dec. 2015, pp.1026-1034.
Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T. Caffe: Convolutional architecture for fast feature embedding. In Proc. the 22nd ACM International Conference on Multimedia, Nov. 2014, pp.675-678.
Felzenszwalb P F, Huttenlocher D P. Efficient graph-based image segmentation. International Journal of Computer Vision, 2004, 59(2): 167-181.
Arbeláez P, Pont-Tuset J, Barron J T, Marques F, Malik J. Multiscale combinatorial grouping. In Proc. the IEEE Conference on Computer Vision and Pattern Recognition, June 2014, pp.328-335.
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al. Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 2015, 115(3): 211-252.
Author information
Authors and Affiliations
Corresponding author
Electronic supplementary material
Below is the link to the electronic supplementary material.
ESM 1
(PDF 609 kb)
Rights and permissions
About this article
Cite this article
Zhang, W., Fang, CW. & Li, GB. Automatic Colorization with Improved Spatial Coherence and Boundary Localization. J. Comput. Sci. Technol. 32, 494–506 (2017). https://doi.org/10.1007/s11390-017-1739-6
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11390-017-1739-6