• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.177-185
• /
• 2022

A method of restoring the occluded area was proposed by referring to images taken with the same types of sensors on high-resolution optical satellite images through deep learning. For the natural continuity of the simulated image with the occlusion region and the surrounding image while maintaining the pixel distribution of the original image as much as possible in the patch segmentation image, CycleGAN (Cycle Generative Adversarial Network) method with ConvNeXt block applied was used to analyze three experimental regions. In addition, We compared the experimental results of a training patch size of 512*512 pixels and a 1024*1024 pixel size that was doubled. As a result of experimenting with three regions with different characteristics,the ConvNeXt CycleGAN methodology showed an improved R² value compared to the existing CycleGAN-applied image and histogram matching image. For the experiment by patch size used for training, an R² value of about 0.98 was generated for a patch of 1024*1024 pixels. Furthermore, As a result of comparing the pixel distribution for each image band, the simulation result trained with a large patch size showed a more similar histogram distribution to the original image. Therefore, by using ConvNeXt CycleGAN, which is more advanced than the image applied with the existing CycleGAN method and the histogram-matching image, it is possible to derive simulation results similar to the original image and perform a successful simulation.

• Journal of the Korea Convergence Society
• /
• v.9 no.6
• /
• pp.45-52
• /
• 2018

In this paper, we propose a linear interpolation method based on patch information generated from a low - resolution image for generating a super resolution image in a single image. Using the regression model of the global space, which is a conventional super resolution generation method, results in poor quality in general because of lack of information to be referred to a specific region. In order to compensate for these results, we propose a method to extract meaningful information by dividing the region into patches in the process of super resolution image generation, analyze the constituents of the image matrix region extended for super resolution image generation, We propose a method of linear interpolation based on optimal patch information that is searched by correlating patch information based on the information gathered before the interpolation process. For the experiment, the original image was compared with the reconstructed image with PSNR and SSIM.

• Journal of Internet of Things and Convergence
• /
• v.9 no.1
• /
• pp.131-138
• /
• 2023

This paper is related to performance improvement of Image-to-Image translation using Relativistic Average Patch GAN and Residual in Residual Dense Block. The purpose of this paper is to improve performance through technical improvements in three aspects to compensate for the shortcomings of the previous pix2pix, a type of Image-to-Image translation. First, unlike the previous pix2pix constructor, it enables deeper learning by using Residual in Residual Block in the part of encoding the input image. Second, since we use a loss function based on Relativistic Average Patch GAN to predict how real the original image is compared to the generated image, both of these images affect adversarial generative learning. Finally, the generator is pre-trained to prevent the discriminator from being learned prematurely. According to the proposed method, it was possible to generate images superior to the previous pix2pix by more than 13% on average at the aspect of FID.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.250-252
• /
• 2022

As immersive video contents have started to emerge in the commercial market, research on it is required. For this, efficient coding methods for immersive video are being studied in the MPEG-I Visual workgroup, and they released Test Model for Immersive Video (TMIV). In current TMIV, the patches are packed into atlas in order of patch size. However, this simple patch packing method can reduce the coding efficiency in terms of 2D encoder. In this paper, we propose patch packing method which pack the patches into atlases by using the similarity of each patch for improving coding efficiency of 3DoF+ video. Experimental result shows that there is a 0.3% BD-rate savings on average over the anchor of TMIV.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.3
• /
• pp.154-161
• /
• 2015

A novel multiframe super-resolution (SR) algorithm is presented to overcome the limitation of existing single-image SR algorithms using motion information from adjacent frames in a video. The proposed SR algorithm consists of three steps: i) definition of a local region using interframe motion vectors, ii) multiscale patch generation and adaptive selection of multiple optimum patches, and iii) combination of optimum patches for super-resolution. The proposed algorithm increases the accuracy of patch selection using motion information and multiscale patches. Experimental results show that the proposed algorithm performs better than existing patch-based SR algorithms in the sense of both subjective and objective measures including the peak signal-to-noise ratio (PSNR) and structural similarity measure (SSIM).

• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1183-1202
• /
• 2017

Image restoration has been carried out by texture synthesis mostly for large regions and inpainting algorithms for small cracks in images. In this paper, we propose a new approach that allows for the simultaneous fill-in of different structures and textures by processing in a wavelet domain. A combination of structure inpainting and patch-based texture synthesis is carried out, which is known as patch-based inpainting, for filling and updating the target region. The wavelet transform is used for its very good multiresolution capabilities. The proposed algorithm uses the wavelet domain subbands to resolve the structure and texture components in smooth approximation and high frequency structural details. The subbands are processed separately by the prioritized patch-based inpainting with isophote energy driven texture synthesis at the core. The algorithm automatically estimates the wavelet coefficients of the target regions of various subbands using optimized patches from the surrounding DWT coefficients. The suggested performance improvement drastically improves execution speed over the existing algorithm. The proposed patch optimization strategy improves the quality of the fill. The fill-in is done with higher priority to structures and isophotes arriving at target boundaries. The effectiveness of the algorithm is demonstrated with natural and textured images with varying textural complexions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4420-4438
• /
• 2021

Image dehazing is an ill-posed problem which is far from being solved. Traditional image dehazing methods often yield mediocre effects and possess substandard processing speed, while modern deep learning methods perform best only in certain datasets. The haze removal effect when processed by said methods is unsatisfactory, meaning the generalization performance fails to meet the requirements. Concurrently, due to the limited processing speed, most dehazing algorithms cannot be employed in the industry. To alleviate said problems, a lightweight fast dehazing network based on a multiple scale-patch framework (MSP) is proposed in the present paper. Firstly, the multi-scale structure is employed as the backbone network and the multi-patch structure as the supplementary network. Dehazing through a single network causes problems, such as loss of object details and color in some image areas, the multi-patch structure was employed for MSP as an information supplement. In the algorithm image processing module, the image is segmented up and down for processed separately. Secondly, MSP generates a clear dehazing effect and significant robustness when targeting real-world homogeneous and nonhomogeneous hazy maps and different datasets. Compared with existing dehazing methods, MSP demonstrated a fast inference speed and the feasibility of real-time processing. The overall size and model parameters of the entire dehazing model are 20.75M and 6.8M, and the processing time for the single image is 0.026s. Experiments on NTIRE 2018 and NTIRE 2020 demonstrate that MSP can achieve superior performance among the state-of-the-art methods, such as PSNR, SSIM, LPIPS, and individual subjective evaluation.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.1
• /
• pp.8-16
• /
• 2011

Image inpainting is a technique for removing damaged regions and reconstructing them with visually plausible backgrounds. However, if size of the damaged regions for reconstructing is large, the unexpected results can be obtained due to disconnected structures within reconstructed regions. In this paper, by considering spatial distance information between candidate patches and a damaged patch as well as pixel value difference, an exemplar-based image inpainting using multiple patches is proposed. In conventional exemplar-based image inpainting method, implausible results such as blocking effects or repetition of reconstructed patch may occur by using inappropriately selected single patch. To improve the exemplar-based method, the weighted sum of multiple patches considering both the spatial distance and the pixel value difference between the target patch and the candidate patches is utilized. Experimental results have shown that the proposed method produces better performance of image inpainting than the existing method.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.10a
• /
• pp.175-175
• /
• 2003

• The Journal of Engineering Research
• /
• v.6 no.2
• /
• pp.99-107
• /
• 2004

In stereo matching system, it is efficient using segment patch, which divides the image into homogeneous region in color or similar intensity, because it preserves the disparity boundary and disparity continuity in low textured region. But many miss matching occur in the highly textured region because of the over segmentation that makes patch small and ambiguous. In this paper, in order to solve problems, we propose adaptive patch matching based on the watershed image segmentation. Performance was verified in experimental results.