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.

Visualization is the process of constructing methods, which are able to synthesize interesting and informative images from data sets, to simplify the process of interpreting the data. In this thesis a new approach to construct meteorological visualization methods using neural network technology is described. The methods are trained with examples instead of explicitely designing the appearance of the visualization. This approach is exemplified using two applications. In the fist the problem to compute an image of the sky for dynamic weather, that is taking account of the current weather state, is addressed. It is a complicated problem to tie the appearance of the sky to a weather state. The method is trained with weather data sets and images of the sky to be able to synthesize a sky image for arbitrary weather conditions. The method has been trained with various kinds of weather and images data. The results show that this is a possible method to construct weather visaualizations, but more work remains in characterizing the weather state and further refinement is required before the full potential of the method can be explored. This approach would make it possible to synthesize sky images of dynamic weather using a fast and efficient empirical method. In the second application the problem of computing synthetic satellite images form numerical forecast data sets is addressed. In this case a mode is trained with preclassified satellite images and forecast data sets to be able to synthesize a satellite image representing arbitrary conditions. The resulting method makes it possible to visualize data sets from numerical weather simulations using synthetic satellite images, but could also be the basis for algorithms based on a preliminary cloud classification. / Report code: LiU-Tek-Lic-2004:66.

Recognizing generic objects by single or multi view range images is a contemporary popular problem in 3D object recognition area with developing technology of scanning devices such as laser range scanners. This problem is vital to current and future vision systems performing shape based matching and classification of the objects in an arbitrary scene. Despite improvements on scanners, there are still imperfections on range scans such as holes or unconnected parts on images. This studyobjects at proposing and comparing algorithms that match a range image to complete 3D models in a target database.The study started with a baseline algorithm which usesstatistical representation of 3D shapesbased on 4D geometricfeatures, namely SURFLET-Pair relations.The feature describes the geometrical relationof a surface-point pair and reflects local and the global characteristics of the object. With the desire of generating solution to the problem,another algorithmthat interpretsSURFLET-Pairslike in the baseline algorithm, in which histograms of the features are used,isconsidered. Moreover, two other methods are proposed by applying 2D space filing curves on range images and applying 4D space filling curves on histograms of SURFLET-Pairs. Wavelet transforms are used for filtering purposes in these algorithms. These methods are tried to be compact, robust, independent on a global coordinate frame and descriptive enough to be distinguish queries&rsquo / categories.Baseline and proposed algorithms are implemented on a database in which range scans of real objects with imperfections are queries while generic 3D objects from various different categories are target dataset.

Doctor of Philosophy(PhD) / This thesis is concerned with the theoretical and practical development of a surface-based mapping algorithm for reliable and robust localization and mapping in prior unknown and unstructured environments. A surface-based map consists of a set of compressed surfaces, processed and represented without geometrical modelling. Each surface in the surface-based map represents an object in the environment. The ability to represent the exact shapes of objects via individual surfaces during the mapping process makes the surface-based mapping algorithm valuable in a number of navigation applications, such as mapping of prior unknown indoor and outdoor unstructured environments, target tracking, path planning and collision avoidance. The ability to unify representations of the same object taken from different viewpoints into a single surface makes the algorithm capable of working in multi-robot mapping applications. A surface-based map of the environment is build incrementally by acquiring the 3D range image of the scene, extracting the objects' surfaces from the 3D range image, aligning the set of extracted surfaces relative to the map and unifying the aligned set of surfaces with surfaces in the map. In the surface unification process the surfaces representing the same object are unified to make a single surface. The thesis introduces the following new methods which are used in the surface-based mapping algorithm: the extraction of surfaces from 3D range images based on a scanned surface continuity check; homogenization of the representation of the non-homogenously sampled surfaces; the alignment of the surface set relative to a large set of surfaces based on surface-based alignment algorithm; evaluating the correspondence between two surfaces based on the overlap area between surfaces; unification of the two surfaces belonging to the same object; and surface unification for a large set of surfaces. The theoretical contributions of this thesis are demonstrated with a series of practical implementations in different outdoor environments.

Doctor of Philosophy(PhD) / This thesis is concerned with the theoretical and practical development of a surface-based mapping algorithm for reliable and robust localization and mapping in prior unknown and unstructured environments. A surface-based map consists of a set of compressed surfaces, processed and represented without geometrical modelling. Each surface in the surface-based map represents an object in the environment. The ability to represent the exact shapes of objects via individual surfaces during the mapping process makes the surface-based mapping algorithm valuable in a number of navigation applications, such as mapping of prior unknown indoor and outdoor unstructured environments, target tracking, path planning and collision avoidance. The ability to unify representations of the same object taken from different viewpoints into a single surface makes the algorithm capable of working in multi-robot mapping applications. A surface-based map of the environment is build incrementally by acquiring the 3D range image of the scene, extracting the objects' surfaces from the 3D range image, aligning the set of extracted surfaces relative to the map and unifying the aligned set of surfaces with surfaces in the map. In the surface unification process the surfaces representing the same object are unified to make a single surface. The thesis introduces the following new methods which are used in the surface-based mapping algorithm: the extraction of surfaces from 3D range images based on a scanned surface continuity check; homogenization of the representation of the non-homogenously sampled surfaces; the alignment of the surface set relative to a large set of surfaces based on surface-based alignment algorithm; evaluating the correspondence between two surfaces based on the overlap area between surfaces; unification of the two surfaces belonging to the same object; and surface unification for a large set of surfaces. The theoretical contributions of this thesis are demonstrated with a series of practical implementations in different outdoor environments.