No description available.

In this thesis work, our main motivation is to create computer aided art work which can eventually transform into a sculpting tool. The work was inspired after Taubin’s work on constructing Hamiltonian triangle strips on quadrilateral meshes. We present an algorithm that can divide a closed 2-manifold surface into exactly two regions, bounded from each other by a single continuous curve. We show that this kind of surface division is possible only if the mesh approximation of a given object is a two colorable quadrilateral mesh. For such a quadrilateral mesh, appropriate texturing of the faces of the mesh using a pair of Truchet tiles will give us a Duotone Surface. Catmull-Clark subdivision can convert any given mesh with arbitrary sided polygons into a two colorable quadrilateral mesh. Using such vertex insertion schemes, we modify the mesh and classify the vertices of the new mesh into two sets. By appropriately texturing each face of the mesh such that the color of the vertices of the face match with the colored regions of the corresponding Truchet tile, we can get a continuous curve that splits the surface of the mesh into two regions. Now, coloring the thus obtained two regions with two different colors gives us a Duotone Surface.

The advancement of computer architecture and chip design has set the stage for the deep learning revolution by supplying enormous computational power. In general, deep learning is built upon neural networks that can be regarded as a universal approximator of any mathematical function. In contrast to model-based machine learning where the representative features are designed by human engineers, deep learning enables the automatic discovery of desirable feature representations based on a data-driven manner. In this thesis, the applications of deep learning to visual content processing and analysis are discussed. For visual content processing, two novel approaches, named LCVSR and RawVSR, are proposed to address the common issues in the filed of Video Super-Resolution (VSR). In LCVSR, a new mechanism based on local dynamic filters via Locally Connected (LC) layers is proposed to implicitly estimate and compensate motions. It avoids the errors caused by the inaccurate explicit estimation of flow maps. Moreover, a global refinement network is proposed to exploit non-local correlations and enhance the spatial consistency of super-resolved frames. In RawVSR, the superiority of camera raw data (where the primitive radiance information is recorded) is harnessed to benefit the reconstruction of High-Resolution (HR) frames. The developed network is in line with the real imaging pipeline, where the super-resolution process serves as a pre-processing unit of ISP. Moreover, a Successive Deep Inference (SDI) module is designed in accordance with the architectural principle suggested by a canonical decomposition result for Hidden Markov Model (HMM) inference, and a reconstruction module is built with elaborately designed Attention based Residual Dense Blocks (ARDBs). For visual content analysis, a new approach, named PSCC-Net, is proposed to detect and localize image manipulations. It consists of two paths: a top-down path that extracts the local and global features from an input image, and a bottom-up path that first distinguishes manipulated images from pristine ones via a detection head, and then localizes forged regions via a progressive mechanism, where manipulation masks are estimated from small scales to large ones, each serving as a prior of the next-scale estimation. Moreover, a Spatio-Channel Correlation Module (SCCM) is proposed to capture both spatial and channel-wise correlations among extracted features, enabling the network to cope with a wide range of manipulation attacks. Extensive experiments validate that the proposed methods in this thesis have achieved the SOTA results and partially addressed the existing issues in previous works. / Dissertation / Doctor of Philosophy (PhD)

Esta dissertação apresenta uma solução prática para o problema de reiluminação de imagens para objetos com geometria arbitrária. Nossa técnica baseia-se no que chamamos de shading proxies (versões deformadas de modelos 3D que aproximam o objeto a ser reiluminado) para guiar o processo de reiluminação. Nosso método é flexível e robusto, podendo reiluminar fotografias, pinturas, e desenhos de diferentes objetos de maneira eficaz. Além de reiluminação, nossa técnica pode ser usada para estimar mapas de normais e profundidade, bem como realizar decomposição intrínsica de imagens, e transferir iluminação para desenhos delineados. Uma avaliação preliminar mostra que nossa técnica produz resultados convincentes, e usuários novatos podem reiluminar imagens facilmente em poucos minutos. / We present a practical solution to the problem of single-image relighting of objects with arbitrary shapes. It is based on a shading-ratio image obtained from the original and target lighting applied to shading proxies (warped versions of 3-D models that approximate the objects to be relit). Our approach is flexible and robust, being applicable to objects with non-uniform albedos. We demonstrate its effectiveness by relighting a large number of photographs, paintings, and drawings containing a variety of objects of different materials. In addition to relighting, our technique can estimate smooth normal and depth maps from pictures, as well as perform intrinsic-image decomposition. Preliminary evaluation has shown that our technique produces convincing results, and novice users can relight images in just a couple of minutes.

Esta dissertação apresenta uma solução prática para o problema de reiluminação de imagens para objetos com geometria arbitrária. Nossa técnica baseia-se no que chamamos de shading proxies (versões deformadas de modelos 3D que aproximam o objeto a ser reiluminado) para guiar o processo de reiluminação. Nosso método é flexível e robusto, podendo reiluminar fotografias, pinturas, e desenhos de diferentes objetos de maneira eficaz. Além de reiluminação, nossa técnica pode ser usada para estimar mapas de normais e profundidade, bem como realizar decomposição intrínsica de imagens, e transferir iluminação para desenhos delineados. Uma avaliação preliminar mostra que nossa técnica produz resultados convincentes, e usuários novatos podem reiluminar imagens facilmente em poucos minutos. / We present a practical solution to the problem of single-image relighting of objects with arbitrary shapes. It is based on a shading-ratio image obtained from the original and target lighting applied to shading proxies (warped versions of 3-D models that approximate the objects to be relit). Our approach is flexible and robust, being applicable to objects with non-uniform albedos. We demonstrate its effectiveness by relighting a large number of photographs, paintings, and drawings containing a variety of objects of different materials. In addition to relighting, our technique can estimate smooth normal and depth maps from pictures, as well as perform intrinsic-image decomposition. Preliminary evaluation has shown that our technique produces convincing results, and novice users can relight images in just a couple of minutes.

Esta dissertação apresenta uma solução prática para o problema de reiluminação de imagens para objetos com geometria arbitrária. Nossa técnica baseia-se no que chamamos de shading proxies (versões deformadas de modelos 3D que aproximam o objeto a ser reiluminado) para guiar o processo de reiluminação. Nosso método é flexível e robusto, podendo reiluminar fotografias, pinturas, e desenhos de diferentes objetos de maneira eficaz. Além de reiluminação, nossa técnica pode ser usada para estimar mapas de normais e profundidade, bem como realizar decomposição intrínsica de imagens, e transferir iluminação para desenhos delineados. Uma avaliação preliminar mostra que nossa técnica produz resultados convincentes, e usuários novatos podem reiluminar imagens facilmente em poucos minutos. / We present a practical solution to the problem of single-image relighting of objects with arbitrary shapes. It is based on a shading-ratio image obtained from the original and target lighting applied to shading proxies (warped versions of 3-D models that approximate the objects to be relit). Our approach is flexible and robust, being applicable to objects with non-uniform albedos. We demonstrate its effectiveness by relighting a large number of photographs, paintings, and drawings containing a variety of objects of different materials. In addition to relighting, our technique can estimate smooth normal and depth maps from pictures, as well as perform intrinsic-image decomposition. Preliminary evaluation has shown that our technique produces convincing results, and novice users can relight images in just a couple of minutes.

In today's social media we see an increase in the use of filters, filters that can distort one's appearance and surroundings, making one wonder what is real and authentic. This essay will analyze two different apps intended for social media that use the popular automated editing tools; Augmented Reality(AR)- and Artificial Intelligence (AI), to find how easily accessible they are and whether the results seem authentic. Through a semiotic approach, I begin the analysis by visually examining the AR and AI filter in the apps to see how they are represented and then what effect it has when applying it on a selected portrait. My findings will contribute to gaining more understanding within the subject of image manipulation and filter, as well as helping me and other graphic designers to increase awareness around consequences when using tools that alter reality.

Thesis (M. Tech.) - Dept. of Visual Arts and Design, Faculty of Human Sciences - Vaal University of Technology. / The digital manipulation of images that are presented as photographs in the media raises issues of interpretation and the possible deception of viewers. The central research question of this study was whether training in the visual arts improves awareness of digital image manipulation of photographs. Secondary aims of the research were to investigate correlations between visual production literacy training and awareness of digital image manipulation of photographs as opposed to general visual literacy training. Secondary aims also include the !investigation of attitudes to the manipulation of photographs in relation to different viewing contexts and various levels of manipulation. The literature review provides background information and theoretical frameworks on the nature of the photographic message and how it is read primarily from a semiotic perspective. A further investigation was done into literature regarding the use of attitudes towards and ethical issues surrounding digital manipulation of photographs. In addition, a review of literature on visual literacy supports the argument that awareness of digital manipulation of photographs should and can be improved. For the empirical component of the study, a total of 145 students at the Vaal University of Technology with low, medium and high visual literacy training participated on a voluntary basis. Both qualitative and quantitative data was gathered through a digitally administered questionnaire on six visual images, each manipulated to a different degree. The results show that production literacy, especially specific training in digital image manipulation software, emerged as the main variable to be significantly (beta coefficient = 0.051; Pearson's r value = 0.436) associated with awareness of manipulation techniques as opposed to general visual literacy (standardised regression coefficieFlt = 0.436; Pearson's r = 0.051 ). Findings regarding attitudes to manipulation and the impact of viewing context show no difference between groups. Emanating from these results possibilities for further research were formulated.

KŘIŠTOVÁ, A.; Identity in photography and art education. [Master's Thesis] Prague 2018 - Charles University, Faculty of Education, Art Education Department, 110 pages. ABSTRACT This Master's Thesis explores the perception and position of identity in society in the context of history and present, based on the approaches of foreign authors dealing with the subject. The theme of identity is situated in the context of visual culture, the history of human portrayal within the visual arts and the portrait photography genre. The concept of the theoretical part is supported by selected authorities from the history of art culture as well as from the field of contemporary art. The theoretical part is the basis for the design of didactic assignments and their following implementation at elementary and secondary schools. Second basic point for the preparation of didactic assignments is obtained from experiences gained with authorial project realization. KEY WORDS: identity, society, visual culture, portrait, photography, digital image, manipulation, intervention

No / In this paper, we investigate how controlled changes to image properties and orientation affect eye movements for repeated viewings of images of natural scenes. We make changes to images by manipulating low-level image content (such as luminance or chromaticity) and/or inverting the image. We measure the effects of these manipulations on human scanpaths (the spatial and chronological path of fixations), additionally comparing these effects to those predicted by a widely used saliency model (L. Itti & C. Koch, 2000). Firstly we find that repeated viewing of a natural image does not significantly modify the previously known repeatability (S. A. Brandt & L. W. Stark, 1997; D. Noton & L. Stark, 1971) of scanpaths. Secondly we find that manipulating image features does not necessarily change the repeatability of scanpaths, but the removal of luminance information has a measurable effect. We also find that image inversion appears to affect scene perception and recognition and may alter fixation selection (although we only find an effect on scanpaths with the additional removal of luminance information). Additionally we confirm that visual saliency as defined by L. Itti and C. Koch's (2000) model is a poor predictor of real observer scanpaths and does not predict the small effects of our image manipulations on scanpaths.