Reinforced Hybrid Wiener Deconvolutional - Convolutional Autoencoders Based Image Deblurring

Grosu, George F; Terebes, Romulus

doi:10.1109/isetc56213.2022.10010278

Cited by 2 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In terms of efficiency, our model demonstrates favorable performance in comparison. As indicated in Table 1, the results reveal that our suggested method surpasses the previously examined techniques [15][16][17][18], according to the specified metrics. The highest SSIM and PSNR values for each measure in Table 1 are highlighted in bold.…”

Section: Resultsmentioning

confidence: 71%

See 1 more Smart Citation

Advancing Image Deblurring Performance with Combined Autoencoder and Customized Hidden Layers

Meysam Gorji, Elham Hafezieh, Ali Tavakoli

2023

tjjpt

View full text Add to dashboard Cite

This article introduces a novel approach to image deblurring by combining a Fourier autoencoder model. The proposed model effectively removes blur artifacts and restores image details by capturing frequency information using the Fourier Transform. In addition, the article presents a method to enhance deblurring by identifying optimal directions using an autoencoder model, trained on a dataset of blurry and sharp images to learn latent features for removing blur and restoring clarity. The encoded representations are used by the decoder to reconstruct a sharper version of the input image. A combination of two autoencoder models is employed, with a Convolutional Neural Network (CNN) handling the initial deblurring process and a fully connected model optimizing the deblurring parameters. This integrated approach leverages the strengths of CNNs in feature extraction and the flexibility of fully connected networks to produce higher quality, clearer images.

show abstract

Section: Resultsmentioning

confidence: 71%

“…This implies that the method might benefit from additional training time or possibly require statistics from the test samples distinct from those in the training set. The SSIM and PSNR values point out that Deblur-GAN+ [15], SRN [16], and MBANet [17] are not as effective as the proposed and HWDCNN [18] models.…”

Section: Resultsmentioning

confidence: 91%