Removing Reflection From a Single Image With Ghosting Effect

Huang, Yan; Quan, Yuhui; Xu, Yong; Xu, Ruotao; Gao, Hui

doi:10.1109/tci.2019.2899320

Cited by 18 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental results demonstrate that the proposed new algorithm is able to achieve superior performance compared with the previous algorithms. Extending the multiscale idea used in our model for dealing with more challenging situations such as ghosting effect [ 15 , 26 ] should be interesting, and this deserves further studies.…”

Section: Discussionmentioning

confidence: 99%

Variational Model for Single-Image Reflection Suppression Based on Multiscale Thresholding

Shao

2022

Sensors

View full text Add to dashboard Cite

Reflections often cause degradation in image quality for pictures taken through glass medium. Removing the undesired reflections is becoming increasingly important. For human vision, it can produce much more pleasing results for multimedia applications. For machine vision, it can benefit various applications such as image segmentation and classification. Reflection removal is itself a highly illposed inverse problem that is very difficult to solve, especially for a single input image. Existing methods mainly rely on various prior information and assumptions to alleviate the ill-posedness. In this paper, we design a variational model based on multiscale hard thresholding to both effectively and efficiently suppress image reflections. A direct solver using the discrete cosine transform for implementing the proposed variational model is also provided. Both synthetic and real glass images are used in the numerical experiments to compare the performance of the proposed algorithm with other representative algorithms. The experimental results show the superiority of our algorithm over the previous ones.

show abstract

Section: Discussionmentioning

confidence: 99%

Variational Model for Single-Image Reflection Suppression Based on Multiscale Thresholding

Shao

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Ref. [ 8 , 9 ] proposed regularization methods based on wavelet transform and a network based on feature sharing strategy for the removal of reflective information from images, respectively.…”

Section: Related Workmentioning

confidence: 99%

Glass Refraction Distortion Object Detection via Abstract Features

Cai

Chen

Sun

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Glass reflection and refraction lead to missing and distorted object feature data, affecting the accuracy of object detection. In order to solve the above problems, this paper proposed a glass refraction distortion object detection via abstract features. The number of parameters of the algorithm is reduced by introducing skip connections and expansion modules with different expansion rates. The abstract feature information of the object is extracted by binary cross-entropy loss. Meanwhile, the abstract feature distance between the object domain and source domain is reduced by a loss function, which improves the accuracy of object detection under glass interference. To verify the effectiveness of the algorithm in this paper, the GRI dataset is produced and made public on GitHub. The algorithm of this paper is compared with the current state-of-the-art Deep Face, VGG Face, TBE-CNN, DA-GAN, PEN-3D, LMZMPM, and the average detection accuracy of our algorithm is 92.57% at the highest, and the number of parameters is only 5.13 M.

show abstract

“…The algorithm not only improves the calculation efficiency, but also ensures the effect of the payment. Huang et al [16] proposed a method to remove ghost images. The algorithm uses the human visual characteristics to find the best stitching line that can bypass the moving object or protruding part according to the energy spectrum technology.…”

Section: Introductionmentioning

confidence: 99%

Optimization of the Progressive Image Mosaicing Algorithm in Fine Art Image Fusion for Virtual Reality

Song

2021

IEEE Access

View full text Add to dashboard Cite

In virtual reality applications, the fade-in and fade-out algorithm based on Bernstein polynomials is a classic method of image fusion. However, this algorithm has certain limitations in image fusion. In this paper, through the analysis and research of the algorithm, the SIFT algorithm is first used to register the image. Secondly, for the disjoint situation of overlapping areas, a progressive image mosaic fusion algorithm in the form of sine function is proposed, which makes it practical and a wider range of applications. It can reflect its characteristics in applications such as virtual reality and art image fusion. Finally, a segmentation technology is added to make the progressive image mosaic fusion algorithm suitable for a variety of overlapping regions, making this algorithm a convenient and flexible image mosaic fusion algorithm. The simulation experiment results show that the progressive mosaic image fusion algorithm proposed in this paper is in good agreement with the spatial details and texture details of highresolution panchromatic images, and the time is shorter, which meets the real-time requirements. INDEX TERMSFine art image fusion; progressive; image mosaic algorithm; virtual reality

show abstract

Removing Reflection From a Single Image With Ghosting Effect

Cited by 18 publications

References 41 publications

Variational Model for Single-Image Reflection Suppression Based on Multiscale Thresholding

Variational Model for Single-Image Reflection Suppression Based on Multiscale Thresholding

Glass Refraction Distortion Object Detection via Abstract Features

Optimization of the Progressive Image Mosaicing Algorithm in Fine Art Image Fusion for Virtual Reality

Contact Info

Product

Resources

About