Abstract: Processes and techniques for imparting three-dimensional visual characteristics to images in a two-dimensional space are described. In one implementation, a graphical image is received in a two-dimensional space (e.g., a user interface on a computing device). A shape palette is presented to a user, the shape palette comprising a visual representation of three-dimensional visual information. Based on user markup of the shape palette, three-dimensional visual information is extracted from the shape palette and correlated with the graphical image. The three-dimensional visual information is processed to render the graphical image with three-dimensional visual characteristics.

Abstract: A system for identifying individuals in digital images and for providing matching digital images is provided. A set of images that include faces of known individuals is received. Faces are detected in the images and facial components are identified in each face. Visual words corresponding to the facial components are generated, stored, and associated with identifiers of the individuals. At a later time, a user may provide an image that includes the face of one of the known individuals. Visual words are determined from the face of the individual in the provided image and matched against the stored visual words. Images associated with matching visual words are ranked and presented to the user.

Abstract: Embodiments related to the removal of blur from an image are disclosed. One disclosed embodiment provides a method of performing an iterative non-blind deconvolution of a blurred image to form an updated image. The method comprises downsampling the blurred image to form a blurred image pyramid comprising images of two or more different resolution scales, downsampling a blur kernel to form a blur kernel pyramid comprising kernels of two or more different sizes, and deconvoluting a selected image in the blurred image pyramid according to a Richardson-Lucy deconvolution process in which a bilateral range/spatial filter is employed.

Abstract: Systems and methods provide drag-and-drop pasting for seamless image composition. In one implementation, a user casually outlines a region of a source image that contains a visual object to be pasted into a target image. An exemplary system automatically calculates a new boundary within this region, such that when pasted at this boundary, visual seams are minimized. The system applies a shortest path calculation to find the optimal pasting boundary. The best path has minimal color variation along its length, thus avoiding structure and visual objects in the target image and providing the best chance for seamlessness. Poisson image editing is applied across this optimized boundary to blend colors. When the visual object being pasted has fine structure at its border that could be truncated by the Poisson editing, the exemplary system integrates the alpha matte of the visual object into the Poisson equations to protect the fine structure.

Abstract: An apparatus and method provide for providing an output image from an input image. The input image may contain at least one portion that does not display certain desired information of the image, such as texture information. The desired information may be obtained from a second portion of the input image and applied to the at least one portion that does not contain the texture information or contains a diminished amount of the texture information. Also, at least one characteristic of the second portion of the input image may not be applied to the at least one portion such as illumination information. In another example, the input image may be decomposed into multiple parts such as a high frequency and a low frequency component. Each component may be hallucinated individually or independently and combined to form the output image.

Abstract: An exemplary method includes providing image data for an illuminated physical sample of a heterogeneous translucent material, determining one or more material properties of the material based in part on a diffusion equation where one of the material properties is a diffusion coefficient for diffusion of radiation in the material and where the determining includes a regularization term for the diffusion coefficient, mapping the one or more material properties to a virtual object volume, assigning virtual illumination conditions to the virtual object volume, and rendering the virtual object volume using the virtual illumination conditions as a boundary condition for a system of diffusion equations of the virtual object volume. Other methods, devices and systems are also disclosed.

Abstract: Described herein is a technology that facilitates efficient large-scale similarity-based retrieval. In several embodiments documents, images, and/or other multimedia files are compactly represented and efficiently indexed to enable robust search using a long-query in a large-scale corpus. As described herein, these techniques include performing decomposition of a file, e.g., a document or document-like representation. The techniques use dimension reduction to obtain three parts, topic-related words (major semantics), document specific words (minor semantics), and background words, representing the major semantics in a feature vector and the minor semantics as keywords. Using the techniques described, file vectors are matched in a topic model and the results ranked based on the keywords.

Abstract: Systems, methods and computer-storage media are provided for identifying low-match search queries and determining comparable item matches to suggest to the user in response to a low-match query. “Low-match queries” are queries for which an insufficient number of exact item matches are available. In embodiments, exact and/or comparable item matches may be determined via semantic analysis. Also provided are systems, methods and computer-storage media for informing the user, by way of a presented indicator, or the like, that a presented item was selected for presentation based upon a similarity metric rather than being determined an exact match for the input query.

Abstract: Systems, methods and computer-storage media are provided for identifying query formulation suggestions in response to receiving a search query. A portion of a search query is received. Query formulation suggestions are identified by semantically analyzing the search query. The query formulation suggestions are used to further formulate the received search query. The query formulation suggestions include semantic-pattern-based query suggestions that are derived from semantic query patterns, one or more entities, and information associated with these entities. The query formulation suggestions are transmitted for presentation.

Abstract: Image resizing for web-based searching is described. In one implementation, a system resizes a user-selected thumbnail image into a larger version of the image that emulates the quality of a large, original image, but without downloading the original image. First, the system extracts resizing parameters when each thumbnail image is created. Then, the system creates a codebook of primitive visual elements extracted from a collection of training images. The primitive visual elements in the codebook provide universal visual parts for reconstructing images. The codebook and a resizing plug-in can be sent once to the user over a background channel. When the user selects a thumbnail image for enlargement, the system resizes the thumbnail image via interpolation and then refines the enlarged image with primitive visual elements from the codebook. The refinement creates an enlarged image that emulates the quality of the large, original image, without downloading the original image.

Abstract: A unified search service may collect information related to an enterprise from at least one of publicly available data and private enterprise data. In some implementations, crowd sourcing may be used to determine a source list of one or more sources of information. Authored content can be generated, such as by combining one or more items of information from the public data with one or more items of information from the private enterprise data. Further, in some implementations, a public index may be generated from the public data, and one or more affiliation indexes may be generated from the private enterprise data. For example, a first affiliation index may contain confidential enterprise information, while a second affiliation index may contain non-confidential enterprise information. A user's affiliation to the enterprise may be taken into consideration when determining which indexes to use when responding to a search request from the user.

Abstract: An exemplary method includes providing image data for an illuminated physical sample of a heterogeneous translucent material, determining one or more material properties of the material based in part on a diffusion equation where one of the material properties is a diffusion coefficient for diffusion of radiation in the material and where the determining includes a regularization term for the diffusion coefficient, mapping the one or more material properties to a virtual object volume, assigning virtual illumination conditions to the virtual object volume, and rendering the virtual object volume using the virtual illumination conditions as a boundary condition for a system of diffusion equations of the virtual object volume. Other methods, devices and systems are also disclosed.

Abstract: The alignment of a sharp image of a subject and a blurred image of the same subject is disclosed. For example, one disclosed embodiment provides a method of determining a series of trial images. The method comprises applying a corresponding series of coordinate transforms to the sharp image, the series of coordinate transforms differing with respect to one or more of a rotational operation and a scaling operation. The method further comprises computing a series blur kernels corresponding to the series of trial images, each blur kernel mapping a trial image from the series of trial images to the blurred image. The method further includes locating a sparsest blur kernel in the series of blur kernels, and identifying one or more of the rotational operation and the scaling operation of the coordinate transform mapping the trial image corresponding to the sparsest blur kernel to the blurred image.

Abstract: A real-time algorithm for rendering of an inhomogeneous scattering media such as smoke under dynamic low-frequency environment lighting is described. An input media animation is represented as a sequence of density fields, each of which is decomposed into a weighted sum of a set of radial basis functions (RBFs) and an optional residual field. Source radiances from single and optionally multiple scattering are directly computed at only the RBF centers and then approximated at other points in the volume using an RBF-based interpolation. Unique approximation techniques are introduced in the computational algorithms to simplify and speed up the computation of source radiance contributed by single and multiple scattering. Using the computed source radiances, a ray marching technique using slice-based integration of radiance along each viewing ray may be performed to render the final image.

Abstract: Image deblurring with blurred/noisy image pairs is described. In one implementation, a system combines a blurred image with a corresponding noisy image of the same subject to create a high-quality deblurred image. The blurred/noisy image pair can be acquired by an inexpensive hand-held camera, e.g., in unfavorable low light conditions. An exemplary iterative process uses the blurred image and the noisy image at each step to produce the high-quality image. First, the system estimates the blur kernel of the blurred image using information from both the blurred and noisy images. Then, the system performs residual image deconvolution, which favors suppression of ringing artifacts. Finally, the system applies gain-controlled deconvolution to suppress remaining ringing artifacts in smooth image regions. The system iterates these steps to obtain the final high-quality image.

Abstract: Search queries containing multiple modes of query input are used to identify responsive results. The search queries can be composed of combinations of keyword or text input, image input, video input, audio input, or other modes of input. The multiple modes of query input can be present in an initial search request, or an initial request containing a single type of query input can be supplemented with a second type of input. In addition to providing responsive results, in some embodiments additional query refinements or suggestions can be made based on the content of the query or the initially responsive results.

Abstract: Image resizing for web-based searching is described. In one implementation, a system resizes a user-selected thumbnail image into a larger version of the image that emulates the quality of a large, original image, but without downloading the original image. First, the system extracts resizing parameters when each thumbnail image is created. Then, the system creates a codebook of primitive visual elements extracted from a collection of training images. The primitive visual elements in the codebook provide universal visual parts for reconstructing images. The codebook and a resizing plug-in can be sent once to the user over a background channel. When the user selects a thumbnail image for enlargement, the system resizes the thumbnail image via interpolation and then refines the enlarged image with primitive visual elements from the codebook. The refinement creates an enlarged image that emulates the quality of the large, original image, without downloading the original image.

Abstract: A real-time algorithm for rendering of an inhomogeneous scattering media such as smoke under dynamic low-frequency environment lighting is described. An input media animation is represented as a sequence of density fields, each of which is decomposed into a weighted sum of a set of radial basis functions (RBFs) and an optional residual field. Source radiances from single and optionally multiple scattering are directly computed at only the RBF centers and then approximated at other points in the volume using an RBF-based interpolation. Unique approximation techniques are introduced in the computational algorithms to simplify and speed up the computation of source radiance contributed by single and multiple scattering. Using the computed source radiances, a ray marching technique using slice-based integration of radiance along each viewing ray may be performed to render the final image.

Abstract: Image resizing for web-based searching is described. In one implementation, a system resizes a user-selected thumbnail image into a larger version of the image that emulates the quality of a large, original image, but without downloading the original image. First, the system extracts resizing parameters when each thumbnail image is created. Then, the system creates a codebook of primitive visual elements extracted from a collection of training images. The primitive visual elements in the codebook provide universal visual parts for reconstructing images. The codebook and a resizing plug-in can be sent once to the user over a background channel. When the user selects a thumbnail image for enlargement, the system resizes the thumbnail image via interpolation and then refines the enlarged image with primitive visual elements from the codebook. The refinement creates an enlarged image that emulates the quality of the large, original image, without downloading the original image.

Abstract: A system for identifying individuals in digital images and for providing matching digital images is provided. A set of images that include faces of known individuals is received. Faces are detected in the images and facial components are identified in each face. Visual words corresponding to the facial components are generated, stored, and associated with identifiers of the individuals. At a later time, a user may provide an image that includes the face of one of the known individuals. Visual words are determined from the face of the individual in the provided image and matched against the stored visual words. Images associated with matching visual words are ranked and presented to the user.