Abstract
Defocus blur detection (DBD) aims to segment the blurred regions from a given image affected by defocus blur. It is a crucial pre-processing step for various computer vision tasks. With the increasing popularity of small mobile devices, there is a need for a computationally efficient method to detect defocus blur accurately. We propose an efficient defocus blur detection method that estimates the probability of each pixel being focused or blurred in resource-constraint devices. Despite remarkable advances made by the recent deep learning-based methods, they still suffer from several challenges such as background clutter, scale sensitivity, indistinguishable low-contrast focused regions from out-of-focus blur, and especially high computational cost and memory requirement. To address the first three challenges, we develop a novel deep network that efficiently detects blur map from the input blurred image. Specifically, we integrate multi-scale features in the deep network to resolve the scale ambiguities and simultaneously modeled the non-local structural correlations in the high-level blur features. To handle the last two issues, we eventually frame our DBD algorithm to perform knowledge distillation by transferring information from the larger teacher network to a compact student network. All the networks are adversarially trained in an end-to-end manner to enforce higher order consistencies between the output and the target distributions. Experimental results demonstrate the state-of-the-art performance of the larger teacher network, while our proposed lightweight DBD model imitates the output of the teacher network without significant loss in accuracy. The codes, pre-trained model weights, and the results will be made publicly available.
- [1] . 2007. Defocus magnification. In Computer Graphics Forum, Vol. 26. 571–579.Google Scholar
- [2] . 2018. Deep depth from defocus: How can defocus blur improve 3D estimation using dense neural networks? In Proceedings of the European Conference on Computer Vision (ECCV’18) Workshops.Google Scholar
- [3] . 2014. Global contrast based salient region detection. IEEE Trans. Pattern Anal. Mach. Intell. 37, 3 (2014), 569–582.Google Scholar
Digital Library
- [4] . 2020. Defocus blur detection via depth distillation. In Proceedings of the European Conference Computer Vision (ECCV’20), Vol. 12358. 747–763.Google Scholar
Digital Library
- [5] . 2009. ImageNet: A large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’09). 248–255.Google Scholar
Cross Ref
- [6] . 2017. Spatially-varying blur detection based on multiscale fused and sorted transform coefficients of gradient magnitudes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17). 596–605.Google Scholar
Cross Ref
- [7] . 2014. Generative adversarial nets. In Proceedings of the Conference on Advances in Neural Information Processing Systems (NeurIPS’14). 2672–2680.Google Scholar
- [8] . 2021. Heterogeneous attention nested U-shaped network for blur detection. IEEE Signal Process. Lett. 29 (2021), 140–144.Google Scholar
- [9] . 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS’17), Vol. 30.Google Scholar
- [10] . 2018. Squeeze-and-excitation networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18). 7132–7141.Google Scholar
Cross Ref
- [11] . 2018. Multiscale blur detection by learning discriminative deep features. Neurocomputing 285 (2018), 154–166.Google Scholar
Cross Ref
- [12] . 2009. Edge detection of images based on improved Sobel operator and genetic algorithms. In Proceedings of the International Conference on Image Analysis and Signal Processing. 31–35.Google Scholar
- [13] . 2019. The relativistic discriminator: A key element missing from standard GAN. In Proceedings of the International Conference on Learning Representations (ICLR’19).Google Scholar
- [14] . 2015. Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations (ICLR’15).Google Scholar
- [15] . 2019. Positional normalization. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS’19). 1620–1632.Google Scholar
- [16] . 2021. Layer-output guided complementary attention learning for image defocus blur detection. IEEE Trans. Image Process. 30 (2021), 3748–3763.Google Scholar
Cross Ref
- [17] . 2020. Why spectral normalization stabilizes GANs: Analysis and improvements. Advances in Neural Information Processing Systems (NeurIPS) 34 (2020), 9652–9638.Google Scholar
- [18] . 2018. Deep blur mapping: Exploiting high-level semantics by deep neural networks. IEEE Trans. Image Process. 27, 10 (2018), 5155–5166.Google Scholar
Cross Ref
- [19] . 2017. Least squares generative adversarial networks. In Proceedings of the IEEE International Conference on Computer Vision (ICCV’17). 2813–2821.Google Scholar
Cross Ref
- [20] . 2019. On the effectiveness of least squares generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 41, 12 (2019), 2947–2960.Google Scholar
Cross Ref
- [21] . 2014. Conditional generative adversarial nets. arXiv:1411.1784. Retrieved from https://arxiv.org/abs/1411.1784.Google Scholar
- [22] . 2018. Spectral normalization for generative adversarial networks. In Proceedings of the International Conference on Learning Representations (ICLR’18).Google Scholar
- [23] . 1998. Robust image corner detection through curvature scale space. IEEE Trans. Pattern Anal. Mach. Intell. 20, 12 (1998), 1376–1381.Google Scholar
Digital Library
- [24] . 2016. Classifying discriminative features for blur detection. IEEE Trans. Cybern. 46, 10 (2016), 2220–2227.Google Scholar
Cross Ref
- [25] . 2017. A unified approach of multi-scale deep and hand-crafted features for defocus estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17). 2760–2769.Google Scholar
Cross Ref
- [26] . 2016. Unsupervised representation learning with deep convolutional generative adversarial networks. In Proceedings of the International Conference on Learning Representations (ICLR’16), and (Eds.).Google Scholar
- [27] . 2015. U-Net: Convolutional networks for biomedical image segmentation. In Proceedings of the Annual Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI’15). 234–241.Google Scholar
Cross Ref
- [28] . 2018. MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18).Google Scholar
Cross Ref
- [29] . 2014. Discriminative blur detection features. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’14). 2965–2972.Google Scholar
Digital Library
- [30] . 2015. Just noticeable defocus blur detection and estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15). 657–665.Google Scholar
Cross Ref
- [31] . 2020. Blur detection via deep pyramid network with recurrent distinction enhanced modules. Neurocomputing 414 (2020), 278–290.Google Scholar
Cross Ref
- [32] . 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the International Conference on Machine Learning (ICML’19).Google Scholar
- [33] . 2021. BR\(^2\)Net: Defocus blur detection via a bidirectional channel attention residual refining network. IEEE Trans. Multimedia 23 (2021), 624–635.Google Scholar
Cross Ref
- [34] . 2022. DeFusionNET: Defocus blur detection via recurrently fusing and refining discriminative multi-scale deep features. IEEE Trans. Pattern Anal. Mach. Intell. 44, 2 (2022), 955–968.Google Scholar
- [35] . 2020. R\(^2\)MRF: Defocus blur detection via recurrently refining multi-scale residual features. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 12063–12070.Google Scholar
- [36] . 2016. A spectral and spatial approach of coarse-to-fine blurred image region detection. IEEE Sign. Process. Lett. 23, 11 (2016), 1652–1656.Google Scholar
Cross Ref
- [37] . 2019. DeFusionNET: Defocus blur detection via recurrently fusing and refining multi-scale deep features. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’19).Google Scholar
Cross Ref
- [38] . 2018. DenseASPP for semantic segmentation in street scenes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18). 3684–3692.Google Scholar
Cross Ref
- [39] . 2016. LBP-Based segmentation of defocus blur. IEEE Trans. Image Process. 25, 4 (2016), 1626–1638.Google Scholar
Digital Library
- [40] . 2019. A local metric for defocus blur detection based on CNN feature learning. IEEE Trans. Image Process. 28, 5 (2019), 2107–2115.Google Scholar
Digital Library
- [41] . 2021. Global context guided hierarchically residual feature refinement network for defocus blur detection. Sign. Process. 183 (2021), 107996.Google Scholar
Cross Ref
- [42] . 2020. Rethinking the defocus blur detection problem and a real-time deep DBD model. In Proceedings of the European Conference Computer Vision (ECCV’20). 617–632.Google Scholar
Digital Library
- [43] . 2021. Defocus blur detection via boosting diversity of deep ensemble networks. IEEE Trans. Image Process. 30 (2021), 5426–5438.Google Scholar
Cross Ref
- [44] . 2021. Self-generated defocus blur detection via dual adversarial discriminators. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’21). 6933–6942.Google Scholar
Cross Ref
- [45] . 2018. Defocus blur detection via multi-stream bottom-top-bottom fully convolutional network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18).Google Scholar
Cross Ref
- [46] . 2019. Defocus blur detection via multi-stream bottom-top-bottom network. IEEE Trans. Pattern Anal. Mach. Intell. 42, 8 (2019), 1884–1897.Google Scholar
- [47] . 2019. Enhancing diversity of defocus blur detectors via cross-ensemble network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’19).Google Scholar
Cross Ref
Index Terms
Distill-DBDGAN: Knowledge Distillation and Adversarial Learning Framework for Defocus Blur Detection
Recommendations
United Defocus Blur Detection and Deblurring via Adversarial Promoting Learning
Computer Vision – ECCV 2022AbstractUnderstanding blur from a single defocused image contains two tasks of defocus detection and deblurring. This paper makes the earliest effort to jointly learn both defocus detection and deblurring without using pixel-level defocus detection ...
Defocus Blur Detection via Depth Distillation
Computer Vision – ECCV 2020AbstractDefocus Blur Detection (DBD) aims to separate in-focus and out-of-focus regions from a single image pixel-wisely. This task has been paid much attention since bokeh effects are widely used in digital cameras and smartphone photography. However, ...
Defocus blur detection based on multiscale SVD fusion in gradient domain
AbstractRecently, defocus blur detection has been an extensive study, but it is still full of challenges in the blur estimation without having any prior knowledge of test image such as blur kernel, degree, or camera parameters. Inspired by the ...






Comments