Skip to main content
SpringerLink
Log in

Coarse-to-fine multi-scale attention-guided network for multi-exposure image fusion

  • Original article
  • Published:
The Visual Computer Aims and scope Submit manuscript

Abstract

In recent years, deep learning networks have achieved prominent success in the field of multi-exposure image fusion. However, it is still challenging to prevent color distortion and blurry edges which leads to bad visual effects. In this paper, we present a multi-scale attention-guided network for multi-exposure image fusion in a coarse-to-fine manner. The network generates multi-scale enhanced attention weight maps of images in different sizes which possess vital details and can emphasize essential regions of interest from both sides. The multi-scale structure can extract features on different scales, and the bilayer structure can extract features from different image sizes. Moreover, we designed a coarse-to-fine attention module to finally generate the weight maps; the module combines channel attention with spatial attention. Fused results will be generated under the guidance of the weight maps. Qualitative and quantitative experiments are performed on a publicly available dataset which shows our method outperforms the state-of-the-art methods in visual effect and objective analysis. Also, ablation experiments prove each part of our method has a great advantage in generating images with significant details, prominent targets, and faithful color.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Data Availability

The data that support the findings of this study are available on request from the corresponding author, X.-K. Shang, upon reasonable request.

References

  1. Zhuang, P., Wu, J., Porikli, F., Li, C.: Underwater image enhancement with hyper-laplacian reflectance priors. IEEE Trans. Image Process. 31, 5442–5455 (2022). https://doi.org/10.1109/TIP.2022.3196546

    Article  PubMed  ADS  Google Scholar 

  2. Jiang, Z., Li, Z., Yang, S., Fan, X., Liu, R.: Target oriented perceptual adversarial fusion network for underwater image enhancement. IEEE Trans. Circuits Syst. Video Technol. 32(10), 6584–6598 (2022)

    Article  Google Scholar 

  3. Liu, J., Wu, Y., Huang, Z., Liu, R., Fan, X.: SMoA: searching a modality-oriented architecture for infrared and visible image fusion. IEEE Signal Process. Lett. 28, 1818–1822 (2021)

    Article  ADS  Google Scholar 

  4. Liu, R., Liu, J., Jiang, Z., Fan, X., Luo, Z.: A bilevel integrated model with data-driven layer ensemble for multi-modality image fusion. IEEE Trans. Image Process. 30, 1261–1274 (2020)

    Article  PubMed  ADS  Google Scholar 

  5. Liu, J., Fan, X., Huang, Z., Wu, G., Liu, R., Zhong, W., Luo, Z.: Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5802–5811 (2022)

  6. Goshtasby, A.A.: Fusion of multi-exposure images. Image Vis. Comput. 23(6), 611–618 (2005). https://doi.org/10.1016/j.imavis.2005.02.004

    Article  Google Scholar 

  7. Li, H., Manjunath, B., Mitra, S.: Multisensor image fusion using the wavelet transform. Gr. Models Image Process. 57(3), 235–245 (1995). https://doi.org/10.1006/gmip.1995.1022

    Article  Google Scholar 

  8. Ma, K., Wang, Z.: Multi-exposure image fusion: a patch-wise approach, pp. 1717–1721 (2015). https://doi.org/10.1109/ICIP.2015.7351094

  9. Li, S., Yang, B., Hu, J.: Performance comparison of different multi-resolution transforms for image fusion. Inf. Fus. 12(2), 74–84 (2011). https://doi.org/10.1016/j.inffus.2010.03.002

    Article  Google Scholar 

  10. Pajares, G., Manuel Cruz, J.: A wavelet-based image fusion tutorial. Pattern Recognit. 37(9), 1855–1872 (2004). https://doi.org/10.1016/j.patcog.2004.03.010

    Article  Google Scholar 

  11. Li, S., Kang, X., Hu, J.: Image fusion with guided filtering. IEEE Trans. Image Process. 22(7), 2864–2875 (2013). https://doi.org/10.1109/TIP.2013.2244222

    Article  PubMed  ADS  Google Scholar 

  12. Mo, Y., Kang, X., Duan, P., Sun, B., Li, S.: Attribute filter based infrared and visible image fusion. Inf. Fus. 75, 41–54 (2021). https://doi.org/10.1016/j.inffus.2021.04.005

    Article  Google Scholar 

  13. Shen, J., Zhao, Y., Yan, S., Li, X.: Exposure fusion using boosting Laplacian pyramid. IEEE Trans. Cybern. 44(9), 1579–1590 (2014). https://doi.org/10.1109/TCYB.2013.2290435

    Article  PubMed  Google Scholar 

  14. Wang, J., Liu, H., He, N.: Exposure fusion based on sparse representation using approximate k-svd. Neurocomputing 135, 145–154 (2014). https://doi.org/10.1016/j.neucom.2013.12.042

    Article  Google Scholar 

  15. Kuang, J., Johnson, G.M., Fairchild, M.D.: iCAM06: A refined image appearance model for HDR image rendering. J. Vis. Commun. Image Represent. 18(5), 406–414 (2007). https://doi.org/10.1016/j.jvcir.2007.06.003

    Article  Google Scholar 

  16. Harsanyi, J., Chang, C.-I.: Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approach. IEEE Trans. Geosci. Remote Sens. 32(4), 779–785 (1994). https://doi.org/10.1109/36.298007

    Article  ADS  Google Scholar 

  17. Zhang, H., Xu, H., Tian, X., Jiang, J., Ma, J.: Image fusion meets deep learning: a survey and perspective. Inf. Fus. 76, 323–336 (2021). https://doi.org/10.1016/j.inffus.2021.06.008

    Article  Google Scholar 

  18. Li, C., et al.: Low-light image and video enhancement using deep learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9396–9416 (2022). https://doi.org/10.1109/TPAMI.2021.3126387

    Article  PubMed  Google Scholar 

  19. Liu, J., Fan, X., Jiang, J., Liu, R., Luo, Z.: Learning a deep multi-scale feature ensemble and an edge-attention guidance for image fusion. IEEE Trans. Circuits Syst. Video Technol. 32(1), 105–119 (2021)

    Article  CAS  Google Scholar 

  20. Zhang, W., et al.: Underwater image enhancement via minimal color loss and locally adaptive contrast enhancement. IEEE Trans. Image Process. 31, 3997–4010 (2022). https://doi.org/10.1109/TIP.2022.3177129

    Article  ADS  Google Scholar 

  21. Liu, R., Jiang, Z., Yang, S., Fan, X.: Twin adversarial contrastive learning for underwater image enhancement and beyond. IEEE Trans. Image Process. 31, 4922–4936 (2022)

    Article  PubMed  ADS  Google Scholar 

  22. Cai, J., Gu, S., Zhang, L.: Learning a deep single image contrast enhancer from multi-exposure images. IEEE Trans. Image Process. 27(4), 2049–2062 (2018). https://doi.org/10.1109/TIP.2018.2794218

    Article  MathSciNet  ADS  Google Scholar 

  23. Hou, X., Zhang, J., Zhou, P.: Reconstructing a high dynamic range image with a deeply unsupervised fusion model. IEEE Photonics J. 13(2), 1–10 (2021). https://doi.org/10.1109/JPHOT.2021.3058740

    Article  CAS  Google Scholar 

  24. Ma, K., Duanmu, Z., Zhu, H., Fang, Y., Wang, Z.: Deep guided learning for fast multi-exposure image fusion. IEEE Trans. Image Process. 29, 2808–2819 (2020). https://doi.org/10.1109/TIP.2019.2952716

    Article  ADS  Google Scholar 

  25. Ma, K., Zeng, K., Wang, Z.: Perceptual quality assessment for multi-exposure image fusion. IEEE Trans. Image Process. 24(11), 3345–3356 (2015). https://doi.org/10.1109/TIP.2015.2442920

    Article  MathSciNet  PubMed  ADS  Google Scholar 

  26. Zhang, Q., Liu, Y., Blum, R.S., Han, J., Tao, D.: Sparse representation based multi-sensor image fusion for multi-focus and multi-modality images: a review. Inf. Fus. 40, 57–75 (2018). https://doi.org/10.1016/j.inffus.2017.05.006

    Article  Google Scholar 

  27. Debevec, P.E., Malik, J.: Recovering high dynamic range radiance maps from photographs, pp. 369-378 (1997). https://doi.org/10.1145/258734.258884

  28. Shan, Q., Jia, J., Brown, M.S.: Globally optimized linear windowed tone mapping. IEEE Trans. Vis. Comput. Gr. 16(4), 663–675 (2010). https://doi.org/10.1109/TVCG.2009.92

    Article  Google Scholar 

  29. Ma, J., Yu, W., Liang, P., Li, C., Jiang, J.: Fusiongan: a generative adversarial network for infrared and visible image fusion. Inf. Fus. 48, 11–26 (2019). https://doi.org/10.1016/j.inffus.2018.09.004

    Article  CAS  Google Scholar 

  30. Liu, J., Wu, G., Luan, J., Jiang, Z., Liu, R., Fan, X.: HoLoCo: Holistic and local contrastive learning network for multi-exposure image fusion. Inf. Fus. 95, 237–249 (2023). https://doi.org/10.1016/j.inffus.2023.02.027

    Article  Google Scholar 

  31. Liu, J., Shang, J., Liu, R., Fan, X.: Attention-guided global-local adversarial learning for detail-preserving multi-exposure image fusion. IEEE Trans. Circuits Syst. Video Technol. 32(8), 5026–5040 (2022)

    Article  Google Scholar 

  32. Jiang, Z., Zhang, Z., Fan, X., Liu, R.: Towards all weather and unobstructed multi-spectral image stitching: algorithm and benchmark, pp. 3783–3791 (2022)

  33. Prabhakar, K., Srikar, V., Babu, R.: Deepfuse: A deep unsupervised approach for exposure fusion with extreme exposure image pairs, pp. 4724–4732 (2017). https://doi.org/10.1109/ICCV.2017.505https://doi.ieeecomputersociety.org/10.1109/ICCV.2017.505

  34. Liu, Z., Yang, J., Yadid-Pecht, O.: Lightfuse: Lightweight CNN based dual-exposure fusion. CoRR abs/2107.02299 (2021). arXiv:2107.02299

  35. Li, H., Wu, X.-J.: Densefuse: a fusion approach to infrared and visible images. IEEE Trans. Image Process. 28(5), 2614–2623 (2019). https://doi.org/10.1109/TIP.2018.2887342

    Article  MathSciNet  ADS  Google Scholar 

  36. Xu, H., Ma, J., Zhang, X.-P.: MEF-GAN: multi-exposure image fusion via generative adversarial networks. IEEE Trans. Image Process. 29, 7203–7216 (2020). https://doi.org/10.1109/TIP.2020.2999855

    Article  ADS  Google Scholar 

  37. Wu, K., Chen, J., Yu, Y., Ma, J.: ACE-MEF: adaptive clarity evaluation-guided network with illumination correction for multi-exposure image fusion. IEEE Trans. Multimed. (2022). https://doi.org/10.1109/TMM.2022.3233299

    Article  Google Scholar 

  38. Qu, L., Liu, S., Wang, M., Song, Z.: Transmef: A transformer-based multi-exposure image fusion framework using self-supervised multi-task learning. In: Proceedings of the AAAI Conference on Artificial Intelligence 36(2), 2126–2134 (2022). https://doi.org/10.1609/aaai.v36i2.20109

  39. Qu, L., Liu, S., Wang, M., Song, Z.: Rethinking multi-exposure image fusion with extreme and diverse exposure levels: a robust framework based on fourier transform and contrastive learning. Inf. Fus. 92, 389–403 (2023). https://doi.org/10.1016/j.inffus.2022.12.002

    Article  Google Scholar 

  40. Ma, J., et al.: Swinfusion: cross-domain long-range learning for general image fusion via swin transformer. IEEE/CAA J. Autom. Sin. 9(7), 1200–1217 (2022). https://doi.org/10.1109/JAS.2022.105686

    Article  Google Scholar 

  41. Chaudhari, S., Mithal, V., Polatkan, G., Ramanath, R.: An attentive survey of attention models. ACM Trans. Intell. Syst. Technol. (2021). https://doi.org/10.1145/3465055

    Article  Google Scholar 

  42. Wang, F., Tax, D. M.J.: Survey on the attention based RNN model and its applications in computer vision. CoRR abs/1601.06823 (2016). arXiv:1601.06823

  43. Chorowski, J. K., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition 28 (2015). https://proceedings.neurips.cc/paper/2015/file/1068c6e4c8051cfd4e9ea8072e3189e2-Paper.pdf

  44. Wang, F. et al.: Residual attention network for image classification (2017)

  45. Galassi, A., Lippi, M., Torroni, P.: Attention in natural language processing. IEEE Trans. Neural Netw. Learn. Syst. 32(10), 4291–4308 (2021). https://doi.org/10.1109/TNNLS.2020.3019893

    Article  PubMed  Google Scholar 

  46. Li, H., Wu, X.-J., Durrani, T.: NestFuse: an infrared and visible image fusion architecture based on nest connection and spatial/channel attention models. IEEE Trans. Instrum. Meas. 69(12), 9645–9656 (2020). https://doi.org/10.1109/TIM.2020.3005230

    Article  ADS  Google Scholar 

  47. Ram Prabhakar, K., Sai Srikar, V., Venkatesh Babu, R.: DeepFuse: a deep unsupervised approach for exposure fusion with extreme exposure image pairs (2017)

  48. Xu, H., Ma, J., Jiang, J., Guo, X., Ling, H.: U2Fusion: a unified unsupervised image fusion network. IEEE Trans. Pattern Anal. Mach. Intell. 44(1), 502–518 (2022). https://doi.org/10.1109/TPAMI.2020.3012548

    Article  PubMed  Google Scholar 

  49. Zhang, Y., et al.: IFCNN: a general image fusion framework based on convolutional neural network. Inf. Fus. 54, 99–118 (2020)

    Article  Google Scholar 

  50. Liu, J., Shang, J., Liu, R., Fan, X.: Halder: Hierarchical attention-guided learning with detail-refinement for multi-exposure image fusion, pp. 1–6 (2021). https://doi.org/10.1109/ICME51207.2021.9428192

  51. Deng, X., Zhang, Y., Xu, M., Gu, S., Duan, Y.: Deep coupled feedback network for joint exposure fusion and image super-resolution. IEEE Trans. Image Process. 30, 3098–3112 (2021). https://doi.org/10.1109/TIP.2021.3058764

    Article  PubMed  ADS  Google Scholar 

  52. Horé, A., Ziou, D.: Image quality metrics: Psnr vs. ssim, pp. 2366–2369 (2010). https://doi.org/10.1109/ICPR.2010.579

Download references

Funding

This work was supported by the National Natural Science Foundation of China under Grant 61906029.

Author information

Author notes

  1. Hao Zhao and Jingrun Zheng contribute equally to this work.

Authors and Affiliations

  1. International School of Information Science and Engineering, Dalian University of Technology, Dalian, China

    Hao Zhao, Jingrun Zheng & Wei Zhong

  2. School of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China

    Xiaoke Shang

  3. Dalian University of Technology Department of Engineering Mechanics, Dalian University of Technology, Dalian, China

    Jinyuan Liu

Authors
  1. Hao Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jingrun Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiaoke Shang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wei Zhong
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jinyuan Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaoke Shang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflicts of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhao, H., Zheng, J., Shang, X. et al. Coarse-to-fine multi-scale attention-guided network for multi-exposure image fusion. Vis Comput 40, 1697–1710 (2024). https://doi.org/10.1007/s00371-023-02880-4

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00371-023-02880-4

Keywords

Search

Navigation