Operadores de tone mapping reverso (RTMOs) realçam imagens e vídeos de baixa faixa dinâmica para visualização em monitores de alta faixa dinâmica. Um problema comum encontrado por operadores anteriores é a maneira com que tratam conteúdo sub ou superexposto. Sob tais condições, eles podem não ser eficientes, e até mesmo causar perda e reversão de contraste visível. Apresentamos uma classe de operadores de tone mapping reverso, baseados no filtro bilateral cruzado (cross bilateral filter), capazes de gerar imagens HDR de alta qualidade. Experimentos utilizando uma métrica objetiva de avaliação de imagens demostram que nosso método é a única técnica capaz de realçar detalhes perceptíveis ao longo de uma grande gama de exposições de imagem, a qual inclui desde imagens subexpostas até imagens superexpostas. / Reverse tone mapping operators (rTMOs) enhance low-dynamic-range images and videos for display on high dynamic range monitors. A common problem faced by previous rTMOs is the handling of under or overexposed content. Under such conditions, they may not be effective, and even cause loss and reversal of visible contrast. We present a class of local rTMOs based on cross bilateral filtering that is capable of generating highquality HDR images and videos for a wide range of exposure conditions. Experiments performed using an objective image quality metric show that our approach is the only single technique available that can gracefully enhance perceived details across a large range of image exposures.

Operadores de tone mapping reverso (RTMOs) realçam imagens e vídeos de baixa faixa dinâmica para visualização em monitores de alta faixa dinâmica. Um problema comum encontrado por operadores anteriores é a maneira com que tratam conteúdo sub ou superexposto. Sob tais condições, eles podem não ser eficientes, e até mesmo causar perda e reversão de contraste visível. Apresentamos uma classe de operadores de tone mapping reverso, baseados no filtro bilateral cruzado (cross bilateral filter), capazes de gerar imagens HDR de alta qualidade. Experimentos utilizando uma métrica objetiva de avaliação de imagens demostram que nosso método é a única técnica capaz de realçar detalhes perceptíveis ao longo de uma grande gama de exposições de imagem, a qual inclui desde imagens subexpostas até imagens superexpostas. / Reverse tone mapping operators (rTMOs) enhance low-dynamic-range images and videos for display on high dynamic range monitors. A common problem faced by previous rTMOs is the handling of under or overexposed content. Under such conditions, they may not be effective, and even cause loss and reversal of visible contrast. We present a class of local rTMOs based on cross bilateral filtering that is capable of generating highquality HDR images and videos for a wide range of exposure conditions. Experiments performed using an objective image quality metric show that our approach is the only single technique available that can gracefully enhance perceived details across a large range of image exposures.

Context. Tone mapping operators (TMO) are designed to reduce the dynamicrange of high dynamic range images so that they can be presented onstandard dynamic range display devices. Many operators focus on creatingperceptually similar images. Objectives. This thesis aims to investigate how dierent TMOs reproducephotographed text. The underlying reason being to test the contrast reproductionof each TMO. Methods. An experiment has been performed in order to investigate thelegibility of photographed and tone mapped text. A user study was conducted,in which 18 respondents partook, where respondents were to ratehow much of the text in each photograph that they found to be legible. Results. Due to low participation, the results of the experiment are mostlyinconclusive. However, some tendencies have been observed and analyzedand they fall in line with previous work within the area. Conclusions. The main conclusion that can be drawn from the results isthat the TMO presented by Kuang [11] is rated as better than the TMOsby Fattal [7] and Kim and Kautz [10].

Les technologies d'écran ont connu récemment une évolution rapide. De la télévision 3D à l'Ultra Haute Définition, la tendance est maintenant aux écrans HDR (pour ''High Dynamic Range'') permettant de reproduire une gamme de luminance bien plus élevée que les écrans classiques. L'émergence de cette technologie implique de nouveaux travaux de standardisation dans le domaine de la compression vidéo. Une question essentielle pour la distribution à grande échelle de contenu HDR est celle de la rétro-compatibilité. Tandis que la future génération d'écrans de télévision sera adaptée à ce nouveau format, il est nécessaire de permettre aux équipements plus anciens de décoder et afficher une version du même contenu dont la dynamique a été préalablement réduite par un procédé appelé ''tone mapping''. Cette thèse vise à explorer les schémas de compression HDR rétro-compatibles. Dans une première approche, un algorithme de tone mapping spécifié par l'encodeur est appliqué à l'image HDR. L'image générée, alors appelée LDR (pour ''Low Dynamic Range''), peut être encodée et décodée dans un format classique. L'encodeur transmet par ailleurs une quantité réduite d'information permettant à un décodeur HDR d'inverser l'opération de tone mapping et de reconstruire une version HDR. L'étude de ces schémas est axée sur la définition de méthodes de tone mapping optimisées pour les performances de compression. La suite de la thèse se concentre sur l'approche scalable dans laquelle les deux versions sont fournies à l'encodeur sans connaissance à priori sur l'opérateur de tone mapping utilisé. Le producteur garde donc le contrôle sur la création du contenu LDR. Cette version LDR est d'abord compressée comme une première couche. L'image reconstruite est utilisée par le codeur scalable pour compresser plus efficacement la couche HDR grâce à un mécanisme de prédiction inter-couches. Notre approche locale et non linéaire nous permet d'améliorer les performances de codage par rapport aux méthodes scalables existantes, en particulier dans le cas où un tone mapping complexe est utilisé pour générer la version LDR. / In recent years, the display technologies have been rapidly evolving. From 3D television to Ultra High Definition, the trend is now towards High Dynamic Range (HDR) displays that can reproduce a luminance range far beyond the capabilities of conventional displays. The emergence of this technology involves new standardization effort in the field of video compression. In terms of large scale content distribution, the question of backward compatibility is critical. While the future generation of television displays will be adapted to this new format, it is necessary to enable the older equipment to decode and display a version of the same content whose dynamic range has been previously reduced by a process called “tone mapping”. This thesis aims at exploring the backward compatible HDR compression schemes. In a first approach, a tone mapping operator specified by the encoder is applied to the HDR image. The resulting image, called Low Dynamic Range (LDR), can then be encoded and decoded in a conventional format. The encoder additionally transmits a small amount of information enabling a HDR capable decoder to inverse the tone mapping operator and retrieve the HDR version. The study of these schemes is directed towards the definition of tone mapping operators optimized for the compression performance. We then focus on scalable approaches, where both versions are given to the encoder without prior knowledge on the tone mapping operator used. The producer thus keeps full control on the LDR content creation process. This LDR version is compressed as a first layer. The reconstructed image is used by the scalable encoder to compress the HDR layer efficiently by performing inter-layer predictions. Thanks to a local and non-linear approach, the proposed schemes improve the coding performance compared to the existing scalable methods, especially in the case where a complex tone mapping is used for generating the LDR version.

Tato práce představuje návrh na vytvoření dekodéru pro video zaznamenané pomocí softwaru Magic Lantern, který může být nainstalován na Canon 5D. Toto video je význačné pro svoji velikost 14-bitů v raw formátu a proto může produkovat velmi kvalitní výstup. Práce má za cíl rozdělit video do jednotlivých snímků, ve vhodném formátu, který umí pracovat také s formáty obrazů s vysokým dynamickým rozsahem.

<p>Imaging in low light is difficult because the number of photons arriving at the image sensor is low. This is a major technological challenge for applications such as surveillance and autonomous driving. Conventional CMOS image sensors (CIS) circumvent this issue by using techniques such as burst photography. However, this process is slow and it does not solve the underlying problem that the CIS cannot efficiently capture the signals arriving at the sensors. This dissertation focuses on solving this problem using a combination of better image sensors (Quanta Image Sensors) and computational imaging techniques.</p> <p><br></p> <p>The first part of the thesis involves understanding how the quanta image sensors work and how they can be used to solve the low light imaging problem. The second part is about the algorithms that can deal with images obtained in low light. The contributions in this part include – 1. Understanding and proposing solutions for the Poisson noise model, 2. Proposing a new machine learning scheme called student-teacher learning for helping neural networks deal with noise, and 3. Developing solutions that work not only for low light but also for a wide range of signal and noise levels. Using the ideas, we can solve a variety of applications in low light, such as color imaging, dynamic scene reconstruction, deblurring, and object detection.</p>

The goal of this thesis is to improve graphical user interface of Tone Mapping Studio(TMS) program. This program is being developed on the Faculty of Information Technology(FIT), Brno University of Technology (BUT) by doc. Ing. Martin Čadík, PhD. The current program is using framework Qt3 , which is old and not compatible with modern libraries. This program has to be rewritten to support current version Qt5. I will analyze other programs in the area of working with High Dynamic Range (HDR) images and video. Changes for improving the interface will be proposed and UX tests will be done. Second part will consist of comparing plug-ins for converting images to grayscale that already exists in TMS.

No description available.

No description available.

Photo editing software allows digital images to be blurred, warped or re-colored at the touch of a button. However, it is not currently possible to change the material appearance of an object except by painstakingly painting over the appropriate pixels. Here we present a set of methods for automatically replacing one material with another, completely different material, starting with only a single high dynamic range image, and an alpha matte specifying the object. Our approach exploits the fact that human vision is surprisingly tolerant of certain (sometimes enormous) physical inaccuracies. Thus, it may be possible to produce a visually compelling illusion of material transformations, without fully reconstructing the lighting or geometry. We employ a range of algorithms depending on the target material. First, an approximate depth map is derived from the image intensities using bilateral filters. The resulting surface normals are then used to map data onto the surface of the object to specify its material appearance. To create transparent or translucent materials, the mapped data are derived from the object's background. To create textured materials, the mapped data are a texture map. The surface normals can also be used to apply arbitrary bidirectional reflectance distribution functions to the surface, allowing us to simulate a wide range of materials. To facilitate the process of material editing, we generate the HDR image with a novel algorithm, that is robust against noise in individual exposures. This ensures that any noise, which would possibly have affected the shape recovery of the objects adversely, will be removed. We also present an algorithm to automatically generate alpha mattes. This algorithm requires as input two images--one where the object is in focus, and one where the background is in focus--and then automatically produces an approximate matte, indicating which pixels belong to the object. The result is then improved by a second algorithm to generate an accurate alpha matte, which can be given as input to our material editing techniques.