• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.9
• /
• pp.4405-4418
• /
• 2016

Automatic image completion techniques have difficulty processing images in which the target region has multiple planes or is non-facade. Here, we propose a new image completion method that uses belief propagation based on planar priorities. We first calculate planar information, which includes planar projection parameters, plane segments, and repetitive regularity extractions within the plane. Next, we convert this planar information into planar guide knowledge using the prior probabilities of patch transforms and offsets. Using the energy of the discrete Markov Random Field (MRF), we then define an objective function for image completion that uses the planar guide knowledge. Finally, in order to effectively optimize the MRF, we propose a new optimization scheme, termed Planar Priority-belief propagation that includes message-scheduling-based planar priority and dynamic label cropping. The results of experiment show that our approach exhibits advanced performance compared with existing approaches.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.517-519
• /
• 2011

본 논문에서는 DIBR(Depth image-based rendering)을 통해 생성되는 3D 영상의 홀을 고품질로 채우는 방법을 제안한다. 이를 위해, 생성된 영상의 깊이도를 고려한 희소성(Sparsity) 기반의 인페인팅 알고리즘을 홀 채우기에 적용하였다. 본 논문에서 제안하는 알고리즘은 홀 주변의 전경 텍스쳐를 제외한 배경 텍스쳐 정보만을 이용하기 때문에, 홀 채우기 시 전경 텍스쳐와 배경 텍스쳐가 혼합되는 문제점이 발생하지 않는다. 또한 희소성 기반의 인페인팅을 이용하기 때문에 에지 정보를 활용한 고품질의 홀 채우기가 가능하다. 본 논문에서 제안하는 알고리즘과 기존의 홀 채우기 알고리즘과의 주관적 화질 비교 결과, 본 논문에서 제안하는 알고리즘의 우수성을 확인할 수 있었다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.6
• /
• pp.48-60
• /
• 2011

Nowadays, the 3D community is actively researching on 3D imaging and free-viewpoint video (FVV). The free-viewpoint rendering in multi-view video, virtually move through the scenes in order to create different viewpoints, has become a popular topic in 3D research that can lead to various applications. However, there are restrictions of cost-effectiveness and occupying large bandwidth in video transmission. An alternative to solve this problem is to generate virtual views using a single texture image and a corresponding depth image. A critical issue on generating virtual views is that the regions occluded by the foreground (FG) objects in the original views may become visible in the synthesized views. Filling this disocclusions (holes) in a visually plausible manner determines the quality of synthesis results. In this paper, a new approach for handling disocclusions using depth based inpainting algorithm in synthesized views is presented. Patch based non-parametric texture synthesis which shows excellent performance has two critical elements: determining where to fill first and determining what patch to be copied. In this work, a noise-robust filling priority using the structure tensor of Hessian matrix is proposed. Moreover, a patch matching algorithm excluding foreground region using depth map and considering epipolar line is proposed. Superiority of the proposed method over the existing methods is proved by comparing the experimental results.

• ETRI Journal
• /
• v.38 no.5
• /
• pp.996-1007
• /
• 2016

This paper presents new hole-filling methods for generating multiview images by using depth image based rendering (DIBR). Holes appear in a depth image captured from 3D sensors and in the multiview images rendered by DIBR. The holes are often found around the background regions of the images because the background is prone to occlusions by the foreground objects. Background-oriented priority and gradient-oriented priority are also introduced to find the order of hole-filling after the DIBR process. In addition, to obtain a sample to fill the hole region, we propose the fusing of depth and color information to obtain a weighted sum of two patches for the depth (or rendered depth) images and a new distance measure to find the best-matched patch for the rendered color images. The conventional method produces jagged edges and a blurry phenomenon in the final results, whereas the proposed method can minimize them, which is quite important for high fidelity in stereo imaging. The experimental results show that, by reducing these errors, the proposed methods can significantly improve the hole-filling quality in the multiview images generated.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.10
• /
• pp.2663-2678
• /
• 2012

Due to sharp depth transition, big holes may be found in the novel view that is synthesized by depth-image-based rendering (DIBR). A hole-filling method based on disparity map is proposed. One important aspect of the method is that the disparity map of destination image is used for hole-filling, instead of the depth image of reference image. Firstly, the big hole detection based on disparity map is conducted, and the start point and the end point of the hole are recorded. Then foreground pixels and background pixels are distinguished for hole-dilating according to disparity map, so that areas with matching errors can be determined and eliminated. In addition, parallaxes of pixels in the area with holes and matching errors are changed to new values. Finally, holes are filled with background pixels from reference image according to these new parallaxes. Experimental results show that the quality of the new view after hole-filling is quite well; and geometric distortions are avoided in destination image, in contrast to the virtual view generated by depth-smoothing methods and image inpainting methods. Moreover, this method is easy for hardware implementation.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.452-455
• /
• 2007

3D stereoscopic viewing of large scale imagery, such as aerial photography and satellite images, needs different parallaxes relative to the display scale. For example, when a viewer sees a stereoscopic image of aerial photography, the optimal parallax of its zoom-in image should be smaller than that of its zoom-out. Therefore, relative parallax adjustment according to the display scale is required. Merely adjusting the spacing between stereo images is not appropriate because the depths of the whole image are either exaggerated or reduced entirely. This paper focuses on the improving stereoscopic viewing with a single remote sensing image and a digital surface model (DSM). We present the parallax adjustment technique to maximize the 3D realistic effect and the visual comfort. For remote sensing data, DSM height value can be regarded as disparity. There are two possible kinds of methods to adjust the relative parallax with a single image performance. One is the DSM compression technique: the other is an adjustment of the distance between the original image and its stereo-mate. In our approach, we carried out a test to evaluate the optimal distance between a single remote sensing image and its stereo-mate, relative to the viewing scale. Several synthetic stereo-mates according to certain viewing scale were created using a parallel projection model and their anaglyphs were estimated visually. The occlusion of the synthetic stereo-mate was restored by the inpainting method using the fields of experts (FoE) model. With the experiments using QuickBird imagery, we could obtain stereoscopic images with optimized parallax at varied display scales.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.5
• /
• pp.54-63
• /
• 2007

The purpose of this study is to present a new energy minimization method for image completion with hierarchical approach. The goal of image completion is to fill in missing part in a possibly large region of an image so that a visually plausible outcome is obtained. An exemplar-based Markov Random Field Modeling(MRF) is proposed in this paper. This model can deal with following problems; detection of global features, flexibility on environmental changes, reduction of computational cost, and generic extension to other related domains such as image inpainting. We use the Priority Belief Propagation(Priority-BP) which is a kind of Belief propagation(BP) algorithms for the optimization of MRF. We propose the hierarchical Priority-BP that reduces the number of nodes in MRF and to apply hierarchical propagation of messages for image completion. We show that our approach which uses hierarchical Priority-BP algorithm in image completion works well on a number of examples.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.8
• /
• pp.67-80
• /
• 2017

This paper presents a hole-filling method using extrapolated spatio-temporal background information to obtain a synthesized view. A new temporal background model using non-overlapped patch based background codebook is introduced to extrapolate temporal background information In addition, a depth-map driven spatial local background estimation is addressed to define spatial background constraints that represent the lower and upper bounds of a background candidate. Background holes are filled by comparing the similarities between the temporal background information and the spatial background constraints. Additionally, a depth map-based ghost removal filter is described to solve the problem of the non-fit between a color image and the corresponding depth map of a virtual view after 3-D warping. Finally, an inpainting is applied to fill in the remaining holes with the priority function that includes a new depth term. The experimental results demonstrated that the proposed method led to results that promised subjective and objective improvement over the state-of-the-art methods.

• Journal of Broadcast Engineering
• /
• v.23 no.4
• /
• pp.503-510
• /
• 2018

Restoring of damaged images is a fundamental problem that was attempted before digital image processing technology appeared. Various algorithms for reconstructing damaged images have been introduced. However, the results show inferior restoration results compared with manual restoration. Recent developments of DNN (Deep Neural Network) have introduced various studies that apply it to image restoration. However, if the wide area is damaged, it can not be solved by a general interpolation method. In this case, it is necessary to reconstruct the damaged area through contextual information of surrounding images. In this paper, we propose an image restoration network using a generative adversarial network (GAN). The proposed system consists of image generation network and discriminator network. The proposed network is verified through experiments that it is possible to recover not only the natural image but also the texture of the original image through the inference of the damaged area in restoring various types of images.

• Journal of the HCI Society of Korea
• /
• v.2 no.2
• /
• pp.11-18
• /
• 2007

We propose a novel method to conceal fiducial markers observed in augmented scenes using patch-based texture synthesis. Despite the efficiency for simple object recognition and tracking, the markers deliver inherent obtrusiveness. They do not only reduce immersiveness, but also severely degrade usability of augmented reality. The proposed method constructs alternative images in real time to overlay markers present in the sequence of images. The global characteristics of background textures are retained and the results are more adaptive to illumination changes.