• Smart Media Journal
• /
• v.5 no.4
• /
• pp.63-68
• /
• 2016

Texture transfer is a method to transfer the texture of an input image into a target image, and is also used for transferring artistic style of the input image. This study presents a real-time texture transfer for generating artistic style video. In order to enhance performance, this paper proposes a parallel framework using T-shape kernel used in general texture transfer on GPU. To accelerate motion computation time which is necessarily required for maintaining temporal coherence, a multi-scaled motion field is proposed in parallel concept. Through these approach, an artistic texture transfer for video with a real-time performance is archived.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06c
• /
• pp.406-407
• /
• 2012

Texture transfer is a NPR technique for expressing various styles according to source (reference) image. By late 2000s, there are many texture transfer researches. But video base researchers are not active. Moreover, they didn't use important feature like directional information which need to express detail characteristics of target. So, we propose a new method to generate texture transfer animation (using video) with directional effect for maintaining temporal coherence and controlling coherence direction of texture. For maintaining temporal coherence, we use optical flow and confidence map to adapt for occlusion/disocclusion boundaries. And we control direction of texture for taking structure of input. For expressing various texture effects according to different regions, we calculate gradient based on directional weight. With these techniques, our algorithm can make animation result that maintain temporal coherence and express directional texture effect. It is reflect the characteristics of source and target image well. And our result can express various texture directions automatically.

• Journal of Fashion Business
• /
• v.13 no.6
• /
• pp.89-98
• /
• 2009

Computer development and new printing technology allow us to express a new type of digital textile designs those were not possible in the past. In this study, watercolor overlaying effect of various colors was tried using airbrush tool in Photoshop program. Photoshop program is a powerful graphic tool and can be used in textile design area to generate various types of designs. Woven texture was also applied to the design to give yarn dyed effects or rich appearance. Photoshop program was also used to develop woven texture without the help of the professional textile CAD. Photoshop channels enables the designers to apply various textures to the image. Plain weave and houndstooth were applied in this study. Colorways of the developed designs having watercolor effect and woven texture by applying Photoshop color adjustment function. Quick and simultaneous changes of colors were possible using this method. The developed textile designs were printed by transfer DTP. Successful textile design prints were expressed and showed watercolor overlaying effect and woven texture. The printed textiles show a little brighter color, and therefore, sample printing is recommendable in case of color sensitive production.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2012.10a
• /
• pp.141-142
• /
• 2012

• Journal of Korea Multimedia Society
• /
• v.11 no.5
• /
• pp.623-632
• /
• 2008

In this paper, we used the color transfer function and the opacity transfer function for the internal 3D object visualization of an image volume data. In transfer function, creating values of between boundaries generally is ambiguous. We concentrated to extract boundary features for segmenting the visual volume rendering objects. Consequently we extracted an image gradient feature in spatial domain and created a multi-dimensional transfer function according to the GPU efficient improvement. Finally using these functions we obtained a good research result as an implementing object boundary visualization of the graphic hardware based 3D texture mapping.

• Nuclear Engineering and Technology
• /
• v.53 no.1
• /
• pp.172-177
• /
• 2021

The microstructure and texture of three 316L foils of 25 ㎛ thickness, which were subjected to different manufacturing process, were systematically characterized using advance analytical techniques. Then, the electrochemical property of the 316L foils in simulated pressurized water reactor (PWR) solution was analyzed using potentiodynamic polarization. The results showed that final rolling strain and annealing temperature had evident effect on grain size, fraction of recrystallization, grain boundary type and texture distribution. It was suggested that large final rolling strain could transfer Brass texture to Copper texture; low annealing temperature could limit the formation of preferable orientations in the rolling process to reduce anisotropy. Potentiodynamic polarization test showed that all samples exhibited good corrosion performance in the simulated primary PWR solution.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.207-215
• /
• 2022

The latest volumetric technology's high geometrical accuracy and realism ensure a high degree of correspondence between the real object and the captured 3D model. Nevertheless, since the 3D model obtained in this way constitutes a sequence as a completely independent 3D model between frames, the consistency of the model surface structure (geometry) is not guaranteed for every frame, and the density of vertices is very high. It can be seen that the interconnection node (Edge) becomes very complicated. 3D models created using this technology are inherently different from models created in movie or video game production pipelines and are not suitable for direct use in applications such as real-time rendering, animation and simulation, and compression. In contrast, our method achieves consistency in the quality of the volumetric 3D model sequence by linking re-meshing, which ensures high consistency of the 3D model surface structure between frames and the gradual deformation and texture transfer through correspondence and matching of non-rigid surfaces. And It maintains the consistency of volumetric 3D model sequence quality and provides post-processing automation.

• Korean Chemical Engineering Research
• /
• v.53 no.6
• /
• pp.814-817
• /
• 2015

A new ionic mass transfer correlation is derived for the fluid-saturated, horizontal porous layer. Darcy-Forchheimer model is used to explain characteristics of fluid motion. Based on the microscales of turbulence a backbone mass transfer relation is derived as a function of the Darcy-Rayleigh number, $Ra_D$ and the porous medium Schmidt number, $Sc_p$. For the Darcy's limit of $Sc_p{\gg}Ra_D$, the Sherwood number, Sh is a function of $Ra_D$ only. However, for the region of high $Ra_D$, Sh can be related with $Ra_DSc_p$. Based on the present backbone equation and the electrochemical mass transfer experiments which are electro plating or electroless plating, the new ionic mass transfer correlation is suggested in the porous media.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.24 no.4
• /
• pp.382-391
• /
• 2021

Unsupervised domain adaptation often gives impressive solutions to handle domain shift of data. Most of current approaches assume that unlabeled target data to train is abundant. This assumption is not always true in practices. To tackle this issue, we propose a general solution to solve the domain gap minimization problem without any target data. Our method consists of two regularization steps. The first step is a pixel regularization by arbitrary style transfer. Recently, some methods bring style transfer algorithms to domain adaptation and domain generalization process. They use style transfer algorithms to remove texture bias in source domain data. We also use style transfer algorithms for removing texture bias, but our method depends on neither domain adaptation nor domain generalization paradigm. The second regularization step is a feature regularization by feature alignment. Adding a feature alignment loss term to the model loss, the model learns domain invariant representation more efficiently. We evaluate our regularization methods from several experiments both on small dataset and large dataset. From the experiments, we show that our model can learn domain invariant representation as much as unsupervised domain adaptation methods.

• Conservation Science in Museum
• /
• v.31
• /
• pp.55-70
• /
• 2024

Style transfer algorithms are currently undergoing active research and are used, for example, to convert ordinary images into classical painting styles. However, such algorithms have yet to produce appropriate results when applied to Korean cultural heritage images, while the number of cases for such applications also remains insufficient. Accordingly, this study attempts to develop a style transfer algorithm that can be applied to styles found among Korean cultural heritage. The algorithm was produced by improving data comprehension by enabling it to learn meaningful characteristics of the styles through representation learning and to separate the cultural heritage from the background in the target images, allowing it to extract the style-relevant areas with the desired color and texture from the style images. This study confirmed that, by doing so, a new image can be created by effectively transferring the characteristics of the style image while maintaining the form of the target image, which thereby enables the transfer of a variety of cultural heritage styles.