Texture Image Inpainting Research Articles

RFA-Net: Residual feature attention network for fine-grained image inpainting

Although most existing methods using Generative Adversarial Networks (GAN) generally produce plausible results, there is a significant amount of artifacts and less-than-ideal restoration of textures when large regions are missing or the background of missing regions is complex. To address this issue, in this paper, we propose a novel texture-aware backbone net named RFA-Net for finer texture image inpainting. Compared to conventional encoder–decoder methods, our main contribution is proposing a novel RFA-Net adopt a non-pooling residual CNN structure with three novel modules, which retains texture features from shallow layers and adaptively learn the importance of certain channels and locations of features that may potentially benefit image inpainting. In addition, we propose a hybrid loss optimization (HLO) module to enable the generator to focus on the semantic and texture details of the inpainted contents. Experimental results demonstrate that our RFA-Net is able to recover texture details and ground-truth consistent images, and outperforms the state-of-the-art methods both in terms of image quality and quantitative metrics. Our source code and data are available online at https://github.com/Jamie-61/RFA-Net-Inpainting.

Research on texture image inpainting of jacquard fabric based on non-single vision

For the texture image inpainting of jacquard fabric with a large damaged region but complete data information around it, traditional exemplar-based image inpainting algorithms are not only have rapid falling traditional confidence value, but also the matching precision is greatly limited due to the lack of robustness, which results in a wrong guided direction and an unsatisfactory inpainting effect. To solve the above-mentioned problems, a novel digital image acquisition system for damaged fabric was designed and one set of texture image inpainting algorithms of jacquard fabric based on non-single vision was developed. In this image inpainting method, the images to be inpainted and target images were obtained through the non-single-vision imaging method. By using the image registration and Poisson image blending technology, the damaged region was filled by block matching first and then patches from the target image to the data missing region were copied. The experimental results clearly showed that the proposed method achieves better results in visual appearance and inpainting quality, compared with traditional approaches for inpainting. In addition, this method shows broad potential application prospects in the virtual restoration of ancient fabrics using image inpainting technology.

Fast algorithm for color texture image inpainting using the non-local CTV model

The classical non-local Total Variation model has been extensively used for gray texture image inpainting previously, but such model can not be directly applied to color texture image inpainting du...

Nonlocal TV-L1 Inpainting Model and its Augmented Lagrangian Algorithm

Nonlocal differential operators have been extensively applied to variational models for image restoration due to its texture-preserving capability. In this paper, we propose a nonlocal TV (total variation)-L1 model for texture image inpainting, which, technically, combines nonlocal operators for regularization term and L1 norm for data term. The former is used to regularize texture and the latter to preserve contrast of images. In addition, we develop augmented Lagrangian algorithm for proposed model by introducing nonlocal auxiliary variable and Lagrangian multiplier. Finally, extensive experiments on synthetic and real texture images are presented to validate the effectiveness and efficiency of our proposed model and algorithm.

Color Texture Image Inpainting Using the Non Local CTV Model

The classical TV (Total Variation) model has been applied to gray texture image denoising and inpainting previously based on the non local operators, but such model can not be directly used to color texture image inpainting due to coupling of different image layers in color images. In order to solve the inpainting problem for color texture images effectively, we propose a non local CTV (Color Total Variation) model. Technically, the proposed model is an extension of local TV model for gray images but we take account of the coupling of different layers in color images and make use of concepts of the non-local operators. As the coupling of different layers for color images in the proposed model will in-crease computational complexity, we also design a fast Split Bregman algorithm. Finally, some numerical experiments are conducted to validate the performance of the proposed model and its algorithm.

Simultaneous cartoon and texture image inpainting using morphological component analysis (MCA)

This paper describes a novel inpainting algorithm that is capable of filling in holes in overlapping texture and cartoon image layers. This algorithm is a direct extension of a recently developed sparse-representation-based image decomposition method called MCA (morphological component analysis), designed for the separation of linearly combined texture and cartoon layers in a given image (see [J.-L. Starck, M. Elad, D.L. Donoho, Image decomposition via the combination of sparse representations and a variational approach, IEEE Trans. Image Process. (2004), in press] and [J.-L. Starck, M. Elad, D.L. Donoho, Redundant multiscale transforms and their application for morphological component analysis, Adv. Imag. Electron Phys. (2004) 132]). In this extension, missing pixels fit naturally into the separation framework, producing separate layers as a by-product of the inpainting process. As opposed to the inpainting system proposed by Bertalmio et al., where image decomposition and filling-in stages were separated as two blocks in an overall system, the new approach considers separation, hole-filling, and denoising as one unified task. We demonstrate the performance of the new approach via several examples.

Simultaneous structure and texture image inpainting

An algorithm for the simultaneous filling-in of texture and structure in regions of missing image information is presented in this paper. The basic idea is to first decompose the image into the sum of two functions with different basic characteristics, and then reconstruct each one of these functions separately with structure and texture filling-in algorithms. The first function used in the decomposition is of bounded variation, representing the underlying image structure, while the second function captures the texture and possible noise. The region of missing information in the bounded variation image is reconstructed using image inpainting algorithms, while the same region in the texture image is filled-in with texture synthesis techniques. The original image is then reconstructed adding back these two sub-images. The novel contribution of this paper is then in the combination of these three previously developed components, image decomposition with inpainting and texture synthesis, which permits the simultaneous use of filling-in algorithms that are suited for different image characteristics. Examples on real images show the advantages of this proposed approach.