A Precise-Mask-Based Method for Enhanced Image Inpainting

Abstract

Mask of damage region is the pretreatment step of the image inpainting, which plays a key role in the ultimate effect. However, state-of-the-art methods have attached significance to the inpainting model, and the mask of damage region is usually selected manually or by the conventional threshold-based method. Since manual method is time-consuming and the threshold-based method does not have the same precision for different images, we herein report a new method for automatically constructing the precise mask by the joint filtering of guided filtering andL0smoothing. It can accurately locate the boundary of damaged region in order to effectively segment the damage region and then greatly improves the ultimate effect of image inpainting. The experimental results show that the proposed method is superior to state-of-the-art methods in the step of constructing inpainting mask, especially for the damaged region with inconspicuous boundary.

Damaged region filling and evaluation by symmetrical exemplar-based image inpainting for Thangka

“…The damaged image region preprocessing and segmentation are complete following related research [24,25]. Several reference and research publications are available [26,27], yet this is not addressed herein. In order to achieve a clear and consecutive narrative, only some simple methods are given for image preprocessing and damaged region segmentation.…”

Telea ve Naiver Stokes Algoritmaları Kullanılarak Görüntülerdeki Bozulmaları Düzeltme

“…Benzer şekilde W. Zhang ve arkadaşları hasar bölgesini etkili bir şekilde bölümlere ayırmak için hasarlı bölgenin sınırını doğru bir şekilde bulabilen ve daha sonra görüntü boyamanın nihai etkisini büyük ölçüde geliştirebilen bir algoritma önermişlerdir. Deneysel sonuçlar, özellikle göze çarpmayan sınırlara sahip hasarlı bölge için, boyama yönteminin oluşturulması aşamasında önerilen yöntemin en gelişmiş yöntemlerden üstün olduğunu göstermektedir [12] Şekil-5: Görüntü boyama işlemi için orijinal girdi görseli ve maske görseli Şekil-6: Telea Algoritması ile görüntü boyama örneği…”

3D Face Image Inpainting with Generative Adversarial Nets

“…Image inpainting, based on convolutional neural networks [9][10][11], has an obvious advantage and is more logical, and inpainting effect is superior to the traditional inpainting method [12]. At the same time, generative adversarial net performs well in feature extraction and in image inpainting [13,14] through the interaction between the generator and discriminator, to repair the missing image.…”