Abstract
Convolutional neural networks have achieved competitive performance in defocus blur detection (DBD). However, due to the different receptive fields of different convolutional layers, there are distinct differences in the features generated by these layers, and the complementary information between cross-level features cannot be fully utilized. Besides, there are still challenges to be solved in homogeneous regions. To tackle the above issues, we focus on both homogeneous region dataset augmentation and model design to propose a novel DBD model based on adaptive cross-level feature fusion and refinement. Specifically, in terms of homogeneous region dataset enhancement, a Laplace filter is used to extract the homogeneous region image patch of the training image to realize homogeneous region image augmentation, which improves the robustness of the model for DBD in the homogeneous region; in terms of model design, we propose an adaptive fusion mechanism with self-learning weights and design the adaptive cross-level feature fusion module, which adaptively discriminates between different levels of features and fuses them step-by-step. In addition, we design the cross-level feature refinement module and embed it into the network, which captures the complementary information of the cross-level features, and refines cross-level feature information from coarse to fine in the decoder stage. Experimental results on two commonly used datasets show that the proposed method outperforms 13 state-of-the-art approaches.
Similar content being viewed by others
Data availability
All data generated or analyzed during this paper can be obtained from the corresponding author on reasonable request.
References
Cai, R., Fang, M.: Blind image quality assessment by simulating the visual cortex. Vis. Comput. (2022). https://doi.org/10.1007/s00371-022-02614-y
Liu, Z., Xiang, Q., Tang, J., Wang, Y., Zhao, P.: Robust salient object detection for RGB images. Vis. Comput. 36, 1823–1835 (2020). https://doi.org/10.1007/s00371-019-01778-4
Zhang, X., Wang, R., Jiang, X., Wang, W., Gao, W.: Spatially variant defocus blur map estimation and deblurring from a single image. J. Vis. Commun. Image Represent. 35(Feb.), 257–264 (2016). https://doi.org/10.1016/j.jvcir.2016.01.002
Jiang, Z., Zhang, Z., Yu, Y., Liu, R.: Publisher Correction: Bilevel modeling investigated generative adversarial framework for image restoration. Vis. Comput. (2022). https://doi.org/10.1007/s00371-022-02713-w
Zhang, K., Zuo, W., Chen, Y., Meng, D., Zhang, L.: Beyond a gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans. Image Process. (2017). https://doi.org/10.1109/TIP.2017.2662206
Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295–307 (2016). https://doi.org/10.1109/TPAMI.2015.2439281
Liu, Z., Liu, J.: Hypergraph attentional convolutional neural network for salient object detection. Vis. Comput. (2022). https://doi.org/10.1007/s00371-022-02499-x
Li, P., Wang, D., Wang, L., Lu, H.: Deep visual tracking: review and experimental comparison. Pattern Recognit. 76, 323–338 (2018)
Liu, R., Li, Z., Jia, J.: Image partial blur detection and classification. IEEE Conf. Comput. Vis. Pattern Recognit. (2008). https://doi.org/10.1109/CVPR.2008.4587465
Pang, Y., Zhu, H., Li, X., Li, X., Pang, Y.: Classifying discriminative features for blur detection. IEEE Trans. Cybern. 46(10), 2220–2227 (2017). https://doi.org/10.1109/TCYB.2015.2472478
Saad, E., Hirakawa, K.: Defocus blur-invariant scale-space feature extractions. IEEE Trans. Image Process. 25(7), 3141–3156 (2016). https://doi.org/10.1109/TIP.2016.2555702
Su, B., Lu, S., Tan, C.L.: Blurred image region detection and classifification. ACM International Conference on Multimedia, pp 1397–1400 (2011)
Zhao, J., Feng, H., Xu, Z., Li, Q., Tao, X.: Automatic blur region segmen tation approach using image matting. Signal Image Video Process. 7(6), 1173–1181 (2013). https://doi.org/10.1007/s11760-012-0381-6
Zhu, X., Cohen, S., Schiller, S., Milanfar, P.: Estimating spatially varying defocus blur from a single image. IEEE Trans. Image Process. 22(12), 4879–4891 (2013). https://doi.org/10.1109/TIP.2013.2279316
Tang, C., Wu, J., Hou, Y., Wang, P., Li, W.: A spectral and spatial approach of coarse-to-fine blurred image region detection. IEEE Signal Process. Lett. (2016). https://doi.org/10.1109/LSP.2016.2611608
Shi, J., Xu, L., Jia, J.: Discriminative blur detection features. IEEE Conf. Comput. Vis. Pattern Recognit. (2014). https://doi.org/10.1109/CVPR.2014.379
Zhang, Y., Hirakawa, K.: Blur processing using double discrete wavelet transform. IEEE Conf. Comput. Vis. Pattern Recognit. (2013). https://doi.org/10.1109/CVPR.2013.145
Vu, C.T., Phan, T.D., Chandler, D.M.: \({ S}_{3}\): a spectral and spatial measure of local perceived sharpness in natural images. IEEE Trans. Image Process. 21(3), 934–945 (2012). https://doi.org/10.1109/TIP.2011.2169974
Zhu, X., Cohen, S., Schiller, S., et al.: Estimating spatially varying defocus blur from a single image. IEEE Trans. Image Process. 22(12), 4879–4891 (2013). https://doi.org/10.1109/TIP.2013.2279316
Golestaneh, S.A., Karam, L.J.: Spatially-varying blur detection based on multiscale fused and sorted transform coeffificients of gradient magnitudes. IEEE Conf. Comput. Vis. Pattern Recognit. (2017). https://doi.org/10.1109/CVPR.2017.71
Tang, C., Wu, J., Hou, Y., Wang, P., Li, W.: A spectral and spatial approach of coarse-to-fifine blurred image region detection. IEEE Signal Process. Lett. 23(11), 1652–1656 (2016). https://doi.org/10.1109/LSP.2016.2611608
Xin, Y., Eramian, M.: LBP-based segmentation of defocus blur. IEEE Trans. Image Process. 25(4), 1–1 (2016). https://doi.org/10.1109/TIP.2016.2528042
Park, J., Tai, Y.W., Cho, D., Kweon, I.S.: A unified approach of multi-scale deep and hand-crafted features for defocus estimation. IEEE Comput. Soc. (2017). https://doi.org/10.1109/CVPR.2017.295
Zhao, W., Zhao, F., Wang, D., Lu, H.: Defocus blur detection via multi-stream bottom-top-bottom fully convolutional network. IEEE Conf. Comput. Vis. Pattern Recognit. (2018). https://doi.org/10.1109/CVPR.2018.00325
Karaali, A., Harte, N., Jung, C.R.: Deep multi-scale feature learning for defocus blur estimation. IEEE Trans. Image Process. 31, 1097–1106 (2022)
Zhao, W., Zheng, B., Lin, Q., Lu, H.: Enhancing diversity of defocus blur detectors via cross-ensemble network. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) (2019). https://doi.org/10.1109/CVPR.2019.00911
Ma, K., Fu, H., Liu, T., Wang, Z., Tao, D.: Deep blur mapping: exploiting high-level semantics by deep neural networks. IEEE Trans. Image Process. 27, 5155–5166 (2018). https://doi.org/10.1109/TIP.2018.2847421
Lee, J., Lee, S., Cho, S., Lee, S.: Deep defocus map estimation using domain adaptation. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) (2019). https://doi.org/10.1109/CVPR.2019.01250
Tang, C., Zhu, X., Liu, X., Wang, L., Zomaya, A.: DeFusionNET: defocus blur detection via recurrently fusing and refining multi-scale deep features. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) (2019). https://doi.org/10.1109/CVPR.2019.00281
Tang, C., Liu, X., Zhu, X., Zhu, E., Sun, K., Wang, P., Wang, L., Zomaya, A.: R\(^{2}\)MRF: defocus blur detection via recurrently refining multi-scale residual features. Proc. AAAI Conf. Artif. Intell. 34(7), 12063–12070 (2020). https://doi.org/10.1609/aaai.v34i07.6884
Zhao, W., Hou, X., He, Y., Lu, H.: Defocus blur detection via boosting diversity of deep ensemble networks. IEEE Trans. Image Process. (2021). https://doi.org/10.1109/TIP.2021.3084101
Li, J., Fan, D., Yang, L., Gu, S., Lu, G., Xu, Y., Zhang, D.: Layer-output guided complementary attention learning for image defocus blur detection. IEEE Trans. Image Process. (2021). https://doi.org/10.1109/TIP.2021.3065171
Zhao, W., Shang, C., Lu, H.: Self-generated defocus blur detection via dual adversarial discriminators. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) (2021). https://doi.org/10.1109/CVPR46437.2021.00686
Jiang, Z., Xu, X., Zhang, L., Zhang, C., Foo, S., Zhu, C.: MA-GANet: a multi-attention generative adversarial network for defocus blur detection. IEEE Trans. Image Process. 31, 3494–3508 (2022). https://doi.org/10.1109/TIP.2022.3171424
Zhao, Z., Yang, H., Luo, H.: Hierarchical edge-aware network for defocus blur detection. Complex Intell. Syst. 8, 4265–4276 (2022). https://doi.org/10.1007/s40747-022-00711-y
Lin, X., Li, H., Cai, Q.: Hierarchical complementary residual attention learning for defocus blur detection. Neurocomputing 501, 88–101 (2022). https://doi.org/10.1016/j.neucom.2022.06.023
Li, J., Liang, B., Lu, X., Li, M., Lu, G., Xu, Y.: From global to local: multi-patch and multi-scale contrastive similarity learning for unsupervised defocus blur detection. IEEE Trans. Image Process. 32, 1158–1169 (2023). https://doi.org/10.1109/TIP.2023.3240856
Abuolaim, A., Brown, M.S.: Defocus Deblurring Using Dual-Pixel Data. European Conference on Computer Vision, Springer, pp 111–126 (2020)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. International Conference on Medical image computing and computer-assisted intervention, Springer, pp 234–241 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2016). https://doi.org/10.1109/CVPR.2016.90
Wei, J., Wang, S., Huang, Q.: F3net: fusion, feedback and focus for salient object detection. AAAI Conf. Artif. Intell. 34, 12321–12328 (2020)
Deng, J., Dong, W., Socher, R., Li, L.J., Kai, L., Li, F.F.: Imagenet: a large-scale hierarchical image database. IEEE Conference on Computer Vision and Pattern Recognition, pp 248–255 (2009)
Fan, D., Cheng, M., Liu, Y., Li, T., Borji, A.: Structure-measure: a new way to evaluate foreground maps. IEEE Int. Conf. Comput. Vis. (ICCV) (2017). https://doi.org/10.1109/ICCV.2017.487
Zhang, K., Wang, T., Luo, W., et al.: MC-Blur: a comprehensive benchmark for image deblurring. IEEE Trans. Circuits Syst. Video Technol. (2023). https://doi.org/10.1109/TCSVT.2023.3319330
Zhang, K., Luo, W., Zhong, Y., et al.: Deblurring by realistic blurring. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 2737–2746 (2020)
Acknowledgements
This work is supported by the Chinese Academy of Sciences-Youth Innovation Promotion Association, Grant Number 2020220, recipient Hang Yang; Key-Area Research and Development Program of Guangdong Province (Grant No. 2019B010155003); Science & Technology Development Project of Jilin Province, Key R &D Programs No. 20210201078GX.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.
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.
About this article
Cite this article
Zhao, Z., Yang, H., Liu, P. et al. Defocus blur detection via adaptive cross-level feature fusion and refinement. Vis Comput (2024). https://doi.org/10.1007/s00371-023-03229-7
Accepted:
Published:
DOI: https://doi.org/10.1007/s00371-023-03229-7