Skip to main content
SpringerLink
Log in

Cross-Camera Deep Colorization

  • Conference paper
  • First Online:
Artificial Intelligence (CICAI 2022)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 13604))

Included in the following conference series:

Abstract

In this paper, we consider the color-plus-mono dual-camera system and propose an end-to-end convolutional neural network to align and fuse images from it in an efficient and cost-effective way. Our method takes cross-domain and cross-scale images as input, and consequently synthesizes HR colorization results to facilitate the trade-off between spatial-temporal resolution and color depth in the single-camera imaging system. In contrast to the previous colorization methods, ours can adapt to color and monochrome cameras with distinctive spatial-temporal resolutions, rendering the flexibility and robustness in practical applications. The key ingredient of our method is a cross-camera alignment module that generates multi-scale correspondences for cross-domain image alignment. Through extensive experiments on various datasets and multiple settings, we validate the flexibility and effectiveness of our approach. Remarkably, our method consistently achieves substantial improvements, i.e., around 10dB PSNR gain, upon the state-of-the-art methods. Code is at: https://github.com/THU-luvision.

This work is supported in part by the Shenzhen Science and Technology Research and Development Funds (JCYJ20180507183706645), in part by the Provincial Key R &D Program of Zhejiang (Serial No. 2021C01016), and the Shenzhen Key Laboratory of next generation interactive media innovative technolog (Funding No. ZDSYS20210623092001004). The lab website is: http://www.luvision.net.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 99.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 129.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Brady, D.J., et al.: Multiscale gigapixel photography. Nature 486(7403), 386–389 (2012)

    Article  Google Scholar 

  2. Bruhn, A., Weickert, J., Schnörr, C.: Lucas/kanade meets horn/schunck: combining local and global optic flow methods. Int. J. Comput. Vis. 61(3), 211–231 (2005)

    Article  MATH  Google Scholar 

  3. Bugeau, A., et al.: Variational exemplar-based image colorization. IEEE TIP (2013)

    Google Scholar 

  4. Cao, X., Tong, X., Dai, Q., Lin, S.: High resolution multispectral video capture with a hybrid camera system. In: CVPR 2011, pp. 297–304. IEEE (2011)

    Google Scholar 

  5. Cao, Y., Zhou, Z., Zhang, W., Yu, Y.: Unsupervised diverse colorization via generative adversarial networks. In: Ceci, M., Hollmén, J., Todorovski, L., Vens, C., Džeroski, S. (eds.) ECML PKDD 2017. LNCS (LNAI), vol. 10534, pp. 151–166. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-71249-9_10

    Chapter  Google Scholar 

  6. Chang, H., et al.: Palette-based photo recoloring. ACM Trans, Graph (2015)

    Google Scholar 

  7. Charpiat, G., Hofmann, M., Schölkopf, B.: Automatic image colorization via multimodal predictions. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5304, pp. 126–139. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-88690-7_10

    Chapter  Google Scholar 

  8. Cheng, Z., Yang, Q., Sheng, B.: Deep colorization. In: ICCV, pp. 415–423 (2015)

    Google Scholar 

  9. Chia, A.Y.S., et al.: Semantic colorization with internet images. In: ACM TOG (2011)

    Google Scholar 

  10. Cossairt, O.S., et al.: Gigapixel computational imaging. In: ICCP. IEEE (2011)

    Google Scholar 

  11. Dong, X., Li, W.: Shoot high-quality color images using dual-lens system with monochrome and color cameras. Neurocomputing 352, 22–32 (2019)

    Article  Google Scholar 

  12. Dosovitskiy, A., et al.: Flownet: learning optical flow with conv networks. In: ICCV (2015)

    Google Scholar 

  13. Goodfellow, I., et al.: Generative adversarial nets. In: NeuIPS, pp. 2672–2680 (2014)

    Google Scholar 

  14. Gupta, R.K., et al.: Image colorization using similar images. In: ACM MM (2012)

    Google Scholar 

  15. HaCohen, Y., Shechtman, E., Goldman, D.B., Lischinski, D.: Non-rigid dense correspondence with applications for image enhancement. ACM TOG 30(4), 1–10 (2011)

    Article  Google Scholar 

  16. He, M., Liao, J., Yuan, L., Sander, P.V.: Neural color transfer between images. arXiv (2017)

    Google Scholar 

  17. He, M., et al.: Deep exemplar-based colorization. In: ACM TOG (2018)

    Google Scholar 

  18. Huang, Y.C., et al.: An adaptive edge detection based colorization algorithm and its applications. In: ACM MM (2005)

    Google Scholar 

  19. Ilg, E., et al.: Flownet 2.0: evolution of optical flow estimation with deep networks. In: CVPR, pp. 2462–2470 (2017)

    Google Scholar 

  20. Ironi, R., et al.: Colorization by example. In: Rendering Techniques. Citeseer (2005)

    Google Scholar 

  21. Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR, pp. 1125–1134 (2017)

    Google Scholar 

  22. Jancsary, J., Nowozin, S., Sharp, T., Rother, C.: Regression tree fields-an efficient, non-parametric approach to image labeling problems. In: CVPR, pp. 2376–2383. IEEE (2012)

    Google Scholar 

  23. Jeon, H.G., et al.: Stereo matching with color and monochrome cameras in low-light conditions. In: CVPR (2016)

    Google Scholar 

  24. Jin, D., et al.: All-in-depth via cross-baseline light field camera. In: ACM MM (2020)

    Google Scholar 

  25. Levin, A., et al.: Colorization using optimization. In: ACM SIGGRAPH 2004 Papers (2004)

    Google Scholar 

  26. Li, G., et al.: Zoom in to the details of human-centric videos. In: ICIP. IEEE (2020)

    Google Scholar 

  27. Liao, J., et al.: Visual attribute transfer through deep image analogy. arXiv (2017)

    Google Scholar 

  28. Liu, C., et al.: Sift flow: Dense correspondence across scenes and its applications. IEEE TPAMI (2010)

    Google Scholar 

  29. Liu, C., Shan, J., Liu, G.: High resolution array camera (Apr 19 2016), US Patent 9,319,585

    Google Scholar 

  30. Liu, X., et al.: Intrinsic colorization. In: ACM SIGGRAPH Asia 2008 papers, pp. 1–9 (2008)

    Google Scholar 

  31. Lohmann, et al.: Space-bandwidth product of optical signals and systems. JOSA A (1996)

    Google Scholar 

  32. Luan, Q., Wen, F., Cohen-Or, D., Liang, L., Xu, Y.Q., Shum, H.Y.: Natural image colorization. In: Eurographics Conference on Rendering Techniques, pp. 309–320 (2007)

    Google Scholar 

  33. Ma, C., Cao, X., Tong, X., Dai, Q., Lin, S.: Acquisition of high spatial and spectral resolution video with a hybrid camera system. IJCV 110(2), 141–155 (2014)

    Article  Google Scholar 

  34. Mantzel, W., et al.: Shift-and-match fusion of color and mono images (2017), US Patent

    Google Scholar 

  35. Reinhard, E., et al.: Color transfer between images. IEEE Comput. Graph. Appl. 21(5), 34–41 (2001)

    Article  Google Scholar 

  36. Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28

    Chapter  Google Scholar 

  37. Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV (2015)

    Google Scholar 

  38. Sharif, S., Jung, Y.J.: Deep color reconstruction for a sparse color sensor. Opt. Express 27(17), 23661–23681 (2019)

    Article  Google Scholar 

  39. Srinivasan, P.P., et al.: Learning to synthesize a 4D RGBD light field from a single image. In: ICCV, pp. 2243–2251 (2017)

    Google Scholar 

  40. Tai, Y.W., Jia, J., Tang, C.K.: Local color transfer via probabilistic segmentation by expectation-maximization. In: CVPR, vol. 1, pp. 747–754. IEEE (2005)

    Google Scholar 

  41. Tai, Y.W., et al.: Image/video deblurring using a hybrid camera. In: CVPR. IEEE (2008)

    Google Scholar 

  42. Tan, Y., et al.: Crossnet++: Cross-scale large-parallax warping for reference-based super-resolution. IEEE TPAMI (2020)

    Google Scholar 

  43. Union, I.T.: Encoding parameters of digital television for studios. CCIR Recommend. (1992)

    Google Scholar 

  44. Vitoria, P., Raad, L., Ballester, C.: Chromagan: An adversarial approach for picture colorization. arXiv preprint arXiv:1907.09837 (2019)

  45. Wang, T.C., et al.: Light field video capture using a learning-based hybrid imaging system. ACM TOG (2017)

    Google Scholar 

  46. Wang, X., et al.: Panda: A gigapixel-level human-centric video dataset. In: CVPR (2020)

    Google Scholar 

  47. Wang, Y., Liu, Y., Heidrich, W., Dai, Q.: The light field attachment: Turning a DSLR into a light field camera using a low budget camera ring. IEEE TVCG 23(10), 2357–2364 (2016)

    Google Scholar 

  48. Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE TIP 13(4), 600–612 (2004)

    Google Scholar 

  49. Welsh, T., Ashikhmin, M., Mueller, K.: Transferring color to greyscale images. In: Annual Conference on Computer Graphics and Interactive Techniques, pp. 277–280 (2002)

    Google Scholar 

  50. Xiao, C., Han, C., Zhang, Z., others, G., He, S.: Example-based colourization via dense encoding pyramids. In: Computer Graphics Forum. Wiley Online Library (2020)

    Google Scholar 

  51. Xue, T., et al.: Video enhancement with task-oriented flow. In: IJCV (2019)

    Google Scholar 

  52. Yatziv, L., Sapiro, G.: Fast image and video colorization using chrominance blending. IEEE Trans. Image Process. 15(5), 1120–1129 (2006)

    Article  Google Scholar 

  53. Yoo, S., Bahng, H., Chung, S., Lee, J., Chang, J., Choo, J.: Coloring with limited data: few-shot colorization via memory augmented networks. In: CVPR, pp. 11283–11292 (2019)

    Google Scholar 

  54. Yuan, X., Fang, L., Dai, Q., Brady, D.J., Liu, Y.: Multiscale gigapixel video: a cross resolution image matching and warping approach. In: ICCP, pp. 1–9. IEEE (2017)

    Google Scholar 

  55. Yuan, X., et al.: A modular hierarchical array camera. Science & Applications, Light (2021)

    Google Scholar 

  56. Zhang, J., Zhu, T., Zhang, A., et al.: Multiscale-VR: multiscale gigapixel 3D panoramic videography for virtual reality. In: ICCP, pp. 1–12. IEEE (2020)

    Google Scholar 

  57. Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR, pp. 586–595 (2018)

    Google Scholar 

  58. Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649–666. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_40

    Chapter  Google Scholar 

  59. Zhao, Y., Li, G., Wang, Z., Lam, E.Y.: Cross-camera human motion transfer by time series analysis. arXiv preprint arXiv:2109.14174 (2021)

  60. Zhao, Y., et al.: EFENet: reference-based video super-resolution with enhanced flow estimation. In: CICAI, pp. 371–383. Springer (2021). https://doi.org/10.1007/978-3-030-93046-2_32

  61. Zhao, Y., et al.: MANet: improving video denoising with a multi-alignment network. arXiv preprint arXiv:2202.09704 (2022)

  62. Zheng, H., Ji, M., Wang, H., Liu, Y., Fang, L.: CrossNet: an end-to-end reference-based super resolution network using cross-scale warping. In: ECCV, pp. 88–104 (2018)

    Google Scholar 

  63. Zhou, B., et al.: Learning deep features for scene recognition using places database. In: NeuIPS, pp. 487–495 (2014)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Tsinghua-Berkeley Shenzhen Institute and Tsinghua Shenzhen International Graduate School, Shenzhen, P.R. China

    Yaping Zhao & Ruqi Huang

  2. Zhejiang Future Technology Institute (Jiaxing), Jiaxing, China

    Yaping Zhao

  3. University of Rochester, Rochester, USA

    Haitian Zheng

  4. Beihang University, Beijing, China

    Mengqi Ji

Authors
  1. Yaping Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Haitian Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mengqi Ji
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ruqi Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ruqi Huang .

Editor information

Editors and Affiliations

  1. Tsinghua University, Beijing, China

    Lu Fang

  2. Xiaomi Inc., Beijing, China

    Daniel Povey

  3. Shanghai Jiao Tong University, Shanghai, China

    Guangtao Zhai

  4. JD Explore Academy, Beijing, China

    Tao Mei

  5. Chinese Academy of Sciences, Beijing, China

    Ruiping Wang

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Zhao, Y., Zheng, H., Ji, M., Huang, R. (2022). Cross-Camera Deep Colorization. In: Fang, L., Povey, D., Zhai, G., Mei, T., Wang, R. (eds) Artificial Intelligence. CICAI 2022. Lecture Notes in Computer Science(), vol 13604. Springer, Cham. https://doi.org/10.1007/978-3-031-20497-5_1

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20497-5_1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20496-8

  • Online ISBN: 978-3-031-20497-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation