Diffusion-based inpainting can be used to repair some damaged parts or remove the undesirable regions in an image. Generally, good visual effects can be achieved after inpainting. However, some traces, such as the differences of local variances and noise pattern, are left in the inpainted image, making it easy for the forensic algorithms to locate the inpainted regions. To eliminate this drawback and achieve an anti-forensics capability, we propose an approach that can remove the traces of the diffusion-based inpainting. Since the pixel values of the inpainted regions are diffused inward by the surrounding pixels, we first analyze the noise pattern of the pixels neighboring the inpainted regions and select the nearby pixels that are directly used for inpainting. After that, a statistical probability model is constructed for each channel in the image, which is used to generate the noise pattern and fill the inpainted regions. Experimental results show that the proposed approach has a good capability for anti-forensics.

Anti-forensics of diffusion-based image inpainting

Recently, deep learning-based techniques have shown great power in image inpainting especially dealing with squared holes. However, they fail to generate plausible results inside the missing regions for irregular and large holes as there is a lack of understanding between missing regions and existing counterparts. To overcome this limitation, we combine two non-local mechanisms including a contextual attention module (CAM) and an implicit diversified Markov random fields (ID-MRF) loss with a multi-scale architecture which uses several dense fusion blocks (DFB) based on the dense combination of dilated convolution to guide the generative network to restore discontinuous and continuous large masked areas. To prevent color discrepancies and grid-like artifacts, we apply the ID-MRF loss to improve the visual appearance by comparing similarities of long-distance feature patches. To further capture the long-term relationship of different regions in large missing regions, we introduce the CAM. Although CAM has the ability to create plausible results via reconstructing refined features, it depends on initial predicted results. Hence, we employ the DFB to obtain larger and more effective receptive fields, which benefits to predict more precise and fine-grained information for CAM. Extensive experiments on two widely-used datasets demonstrate that our proposed framework significantly outperforms the state-of-the-art approaches both in quantity and quality.

Non-Local and Multi-Scale Mechanisms for Image Inpainting.

Saturated highlights on metal surfaces reduce the detection accuracy of fuel nozzles. In this paper, we propose an image inpainting method with a saturated highlight based on the statistics of similar patches used in prior segmentation of the subregion. The sequence image acquisition is based on the shape from focus in the five-axis platform. By our method, the focus measure (FM) operator and the window size are evaluated using the sharpness evaluation curve and calculating time. We observe that the detection accuracy is improved when the highlight area is filled by the highlight-free area within the same segmentation region. There are fewer deviation points in the three-dimensional (3D) point cloud that are extracted from the sequence images. The inlet circle and the outlet circle of the fuel nozzle are both detected by the two-dimensional (2D) Hough Transform (HT) method. Our experiments show that the method yields better results in 3D detection of the key parameters of fuel nozzles with the saturated highlight characteristics.

/pdf/3d-measurement-method-for-saturated-highlight-30uwv8lk.pdf

3D Measurement Method for Saturated Highlight Characteristics on Surface of Fuel Nozzle

In this article, a blockwise regression-based image inpainting framework is proposed. The core idea is to fill the unknown region in two stages: Extrapolate the edges to the unknown region and then...

A Novel Image Inpainting Framework Using Regression

The process of recovering the damaged or missing areas from an image utilizing information as of known portions is termed Image Inpainting. To refurbish the damaged image into a new one alike an actual image, numerous sophisticated methodologies have been established to date. Nevertheless, in the case of images with a larger missing region, these models are not effective in addressing the problem. Likewise, these methodologies are ineffective towards the edge. Therefore, by utilizing the Log of Exponent Rule Generative Adversarial Network algorithm, a novel clustering-centric image inpainting system has been proposed here. Initially, two significant steps, namely (i) noise removal, and (ii) Contrast Enhancement (CE), are performed to pre-process the input images. After that, by utilizing the Adaptive Max One-Sided Box Filter (AMOSBF) algorithm, the pre-processed images’ edges are well-preserved. Then, the most needed features are extracted as of the edge preserved images. Next, by employing Supremum Distance Fast Density Peaks Clustering Algorithm (SDFDPCA), the features being extracted are clustered. Next, the proposed model, termed Log of Exponent Rule Mish Generative Adversarial Network (LOERMGAN), which reconstructs the actual images effectively, is fed with the clustered features and also the masked image and the mask itself. In this research, the openly accessible datasets termed ADE20k, Paris, and Places2 are utilized. Subsequently, the outcomes obtained are analogized with the prevailing methodologies. The experiential outcomes displayed that the proposed model outshines the other prevailing methodologies by effectively reconstructing images.

https://dl.acm.org/doi/pdf/10.1145/3574131.3574440

A Novel Clustering-Based Image Inpainting Model Using the Loermgan Algorithm

Image inpainting technique recovers the missing regions of an image using information from known regions and it has shown success in various application fields. As a popular kind of methods, Markov Random Field (MRF)-based methods are able to produce better results than earlier diffusion-based and sparse-based methods on inpainting images with big holes. However, for images with complex structures, the results are still not quite pleasant and some inpainting trails exist. The direction feature is an important factor for image understanding and human eye visual requirements, and exploiting multi-direction features is of great potential to further improve inpainting performance. Following the idea, this paper proposes a Structure Offsets Statistics based image inpainting algorithm by exploiting multiple direction features under the framework of MRF-based methods. Specifically, when selecting proper labels, multi-direction features are extracted and applied to construct a structure image and a non-structure image, and the candidate labels are chosen from the offsets of structure and non-structure images. Meanwhile, the multi-direction features are applied to construct a new smooth term for the energy equation which is then solved by graph-cut optimization technology. Experimental results show that on inpainting tasks with various complexities, the proposed method is superior to several state-of-the-art approaches in terms of the abilities of maintaining structure coherence and neighborhood consistence and the computational efficiency.

/pdf/exploiting-multi-direction-features-in-mrf-based-image-1icb72dn1b.pdf

Zhidan Li

Papers

Exploiting Multi-Direction Features in MRF-Based Image Inpainting Approaches