Global context guided hierarchically residual feature refinement network for defocus blur detection

Zhai, Yongping; Wang, Junhua; Deng, Jinsheng; Yue, Guanghui; Zhang, Wei; Tang, Chang

doi:10.1016/j.sigpro.2021.107996

Cited by 8 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two methods [18,21] used a similar approach of extraction from local integral values of the images but used either a fixed static threshold or from a specified range. is hard-coded threshold scheme results in performance degradation, as shown in FFT [23] LIU [9] hifst [25] SHI [35] SVD [24] LTP International Journal of Optics Figure 11 where [21] is unable to detect the regions in the image, whereas the proposed method used an adaptive threshold computed using the deviation between the neighboring pixels and performed very well. Our experiments further reveal that the results of [18,21] indicate the gaps between the extracted sharp regions, whereas the proposed method produced the filled regions approximately.…”

Section: Discussionmentioning

confidence: 99%

“…is provides significantly better results due to the large deviation of the region. Our results indicate that the pixel selection based on a small number of adjacent pixels affects the SHI [12] BTB [34] DNET [31] Proposed DBDF [35] KSFV [27] LBP [21] DHDE [30] HIFST [25] DBDF [35] DHDE [30] DNET [31] HIFST [25] Proposed LBP [21] KSFV [27] SHI [12] SVD [24] Precision Recall F1-Score results, whereas using a large number of adjacent pixels to determine the pixel selection leads to good results. Existing defocus blur detection methods, based on using the integral values directly, fail to operate well for the motion blur.…”

Section: Discussionmentioning

confidence: 99%

“…Tang et al [34] proposed a Deep Neural Network (DNN) based technique Diffusion Network (DNet) that fused the refined features extracted by the networks to obtain the segmented blur and sharp regions. In [35], the author introduced global context-guided hierarchically residual feature refinement network "HRFRNet." e hierarchical features are used to enhance the final outcomes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Robust Approach for Blur and Sharp Regions’ Detection Using Multisequential Deviated Patterns

Khan

Javed

Irtaza

et al. 2021

International Journal of Optics

View full text Add to dashboard Cite

Blur detection (BD) is an important and challenging task in digital imaging and computer vision applications. Accurate segmentation of homogenous smooth and blur regions, low-contrast focal regions, missing patches, and background clutter, without having any prior information about the blur, are the fundamental challenges of BD. Previous work on BD has emphasized much effort on designing local sharpness metric maps from the images. However, the smooth/blurred regions having the same patterns as sharp regions make them problematic. This paper presents a robust novel method to extract the local metric map for blurred and nonblurred regions based on multisequential deviated patterns (MSDPs). Unlike the preceding, MSDP extracts the local sharpness metric map on the images at multiple scales using different adaptive thresholds to overcome the problems of smooth/blur regions and missing patches. By using the integral values of the image along with image masking and Otsu thresholding, highly accurate segmented regions of the images are acquired. We argue/hypothesize that the local sharpness map extraction by using direct integral information of the image is highly affected by the threshold selected for distinction between the regions, whereas MSDP feature extraction overcomes the limitations substantially by using automatic threshold computation over multiple scales of the images. Moreover, the proposed method extracts the relatively accurate sharp regions from the high-dense blur and noisy images. Experiments are conducted on two commonly used SHI and DUT datasets for blur and sharp region classifications. The results indicate the effectiveness of the proposed method in terms of sharp segmented regions. Experimental results of qualitative and quantitative comparisons of the proposed method with ten comparative methods demonstrate the superiority of our method. Moreover, the proposed method is also computationally efficient over state-of-the-art methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Robust Approach for Blur and Sharp Regions’ Detection Using Multisequential Deviated Patterns

Khan

Javed

Irtaza

et al. 2021

International Journal of Optics

View full text Add to dashboard Cite

show abstract

“…The CNN is trained using blurred patches to estimate the optimum parameter based on blurriness to achieve the best sharpening result. In [36][37][38][39][40] a CNN architecture is proposed for end to end defocus map estimation, these networks were trained using either natural or synthetic images labelled at a pixel level to segment focused regions on the image, producing outstanding results. Li et al [41] on the other hand, proposed a CNN-based method to estimate spatially varying defocus blur on a single image, using synthetic data to train the network and domain transfer to bridge the gap between real and synthetic images.…”

Section: Introductionmentioning

confidence: 99%

“…Inspired by these works, the motivation of this study is to explore the application of deep neural networks in solving the challenging problem of estimating the defocus map from a single image. The main contribution of this work is that, unlike previous works [36][37][38][39][40], we treat the blurriness estimation as a self-supervised multi-class classification problem which is solved by training a CNN to classify a patch of the input image into one of the 20 levels of blurriness. The output of the CNN is a patch-based estimation of blurriness.…”

Section: Introductionmentioning

confidence: 99%

Single image deep defocus estimation and its applications

Galetto

Deng

2021

Preprint

View full text Add to dashboard Cite

The depth information is useful in many image processing applications. However, since taking a picture is a process of projection of a 3D scene onto a 2D imaging sensor, the depth information is embedded in the image. Extracting the depth information from the image is a challenging task. A guiding principle is that the level of blurriness due to defocus is related to the distance between the object and the focal plane. Based on this principle and the widely used assumption that Gaussian blur is a good model for defocus blur, we formulate the problem of estimating the spatially varying defocus blurriness as a Gaussian blur classification problem. We solved the problem by training a deep neural network to classify image patches into one of the 20 levels of blurriness. We have created a dataset of more than 500000 image patches of size 32x32 which are used to train and test several well-known network models. We find that MobileNetV2 is suitable for this application due to its low memory requirement and high accuracy. The trained model is used to determine the patch blurriness which is then refined by applying an iterative weighted guided filter. The result is a defocus map that carries the information of the degree of blurriness for each pixel. We compare the proposed method with state-of-the-art techniques and we demonstrate its successful applications in adaptive image enhancement, defocus magnification, and multi-focus image fusion.

show abstract

Single image defocus map estimation through patch blurriness classification and its applications

Galetto

Deng

2022

Vis Comput

View full text Add to dashboard Cite

Depth information is useful in many image processing applications. However, since taking a picture is a process of projection of a 3D scene onto a 2D imaging sensor, the depth information is embedded in the image. Extracting the depth information from the image is a challenging task. A guiding principle is that the level of blurriness due to defocus is related to the distance between the object and the focal plane. Based on this principle and the widely used assumption that Gaussian blur is a good model for defocus blur, we formulate the problem of estimating the spatially varying defocus blurriness as a Gaussian blur classification problem. We solve the problem by training a deep neural network to classify image patches into one of the 20 levels of blurriness. We have created a dataset of more than 500,000 image patches of size $$32\times 32$$ 32 × 32 which does not require human labelling. The dataset is used to train and test several well-known network models. We find that MobileNetV2 is suitable for this application due to its low memory requirement and high accuracy. The trained model is used to determine the patch blurriness which is then refined by applying an iterative weighted guided filter. The result is a defocus map that carries the information of the degree of blurriness for each pixel. We compare the proposed method with state-of-the-art techniques and we demonstrate its successful applications in adaptive image enhancement and defocus magnification limited to images that present a clear distinction between defocus levels.

show abstract

Global context guided hierarchically residual feature refinement network for defocus blur detection

Cited by 8 publications

References 27 publications

A Robust Approach for Blur and Sharp Regions’ Detection Using Multisequential Deviated Patterns

A Robust Approach for Blur and Sharp Regions’ Detection Using Multisequential Deviated Patterns

Single image deep defocus estimation and its applications

Single image defocus map estimation through patch blurriness classification and its applications

Contact Info

Product

Resources

About