Abstract: A technique for digital stereo imaging is provided.

Abstract: An apparatus for generating a panoramic image(s) may include a processor and memory storing executable computer code causing the apparatus to at least perform operations including generating a panoramic image(s) based on performing registration on at least two images associated with depth map data and determining an overlap region(s) between the two images within first and second items of depth map data. The computer program code may further cause the apparatus to label the overlap region(s) within the first or second item of depth map data based on generating a virtual seam(s) connecting portions of the two images to generate a composite image. The portions correspond to image data within first and second items of depth map data. The computer program code may further cause the apparatus to blend the seam of the composite image to obtain the panoramic image. Corresponding methods and computer program products are also provided.

Abstract: In an example embodiment, a method, apparatus and computer program product are provided. The method includes facilitating receipt of a plurality of light-field images of a scene captured in a burst capture by a light-field camera. The method includes determining shifts between images of the plurality of light-field images, where the shifts between the images of the plurality of light-field images are associated with shake of the light-field camera while capturing the plurality of light-field images. The method includes generating a plurality of depth maps for the plurality of light-field images, and generating a set of view images of the scene based on the plurality of light-field images and the plurality of depth maps. The method includes generating a refocus image by combining the set of view images based at least on the shifts between the images of the plurality of light-field images.

Abstract: A method, apparatus, and computer program product for generating a seamless and error-free panorama image using a selective set of views from a multi-view image from each of the several captured light field (LF) images. The method identifies the view and corresponding image for each captured LF image which has the same or closely located center of projection with the views of neighboring LF images. Image registration and warping techniques are applied across the images and the parallax error is calculated which indicates the closeness of their center of projections. The view from each LF captured image with minimal parallax error is selected and stitched together with the other views identified as having minimal parallax error.

Abstract: A technique for digital stereo imaging is provided.

Abstract: An apparatus comprising: a depth map estimator configured to determine, associated with at least one visual image, a depth map comprising at least one distance value in a direction relative to an apparatus; a direction of arrival estimator configured to determine, using at least two microphones, at least one audio source signal with a direction; and an audio signal processor configured to process the at least one audio source signal based on the at least one distance value in the direction of the at least one audio source signal.

Abstract: A method, apparatus and computer program for controlling a digital microlens array camera to obtain a sequence of images each including microimages captured by respective microlenses; for determining in each of the images a set of diffused microimages in which an optical communication light source is diffused over each of the microimages of the set; and for decoding optically communicated information from the set.

Abstract: In an example embodiment, a method, apparatus and computer program product are provided. The method includes computing a first cost volume for a light-field image. A first depth map comprising depth information of the plurality of sub-images of the light-field image is computed based on the first cost volume. A first view image comprising reconstruction information is reconstructed based on the depth information of the plurality of sub-images. A second cost volume corresponding to the first cost volume is computed based on the reconstruction information. The second cost volume is filtered based on the first view image to generate an aggregated cost volume. A second depth map is generated based on the aggregated cost volume. The second depth map facilitates generation of a second view image that is associated with a resolution higher than a resolution of the first view image.

Abstract: In accordance with various example embodiments, methods, apparatuses, and computer program products are provided. A method comprises accessing a gallery comprising a plurality of classes, determining distances between classes of the plurality of classes, and determining thresholds for one or more classes of the gallery for classifying test objects in the classes, wherein threshold for a class is determined based on at least one distance of the class from at least one remaining class of the plurality of classes. The apparatus comprises at least one processor and at least one memory, configured to, cause the apparatus to perform accessing a gallery comprising a plurality of classes, determining distances between classes of the plurality of classes, and determining thresholds for classes of the gallery for classifying test objects in the classes, wherein threshold for a class is determined based on distances of the class from remaining classes of the gallery.

Abstract: In an example embodiment a method, apparatus and computer program product are provided. The method includes facilitating receipt of a light-field image, determining one or more depth levels in the light-field image and generating a plurality of images from the light-field image. The method includes determining one or more registration matrices corresponding to the one or more depth levels between an image and one or more remaining images of the plurality of images. The method includes performing a super-resolution of the image and the one or more remaining images based on the one or more registration matrices to generate a super-resolved image of the image.

Abstract: A method, apparatus and computer program for controlling a digital microlens array camera to obtain a sequence of images each including microimages captured by respective microlenses; for determining in each of the images a set of diffused microimages in which an optical communication light source is diffused over each of the microimages of the set; and for decoding optically communicated information from the set.

Abstract: An apparatus including a first optical element, a second optical element and an image sensor. The first optical element is configured to focus light with first wavelengths on the second optical element, and the second optical element is invisible to light with second wavelengths and configured to relay an image containing lightfield information on the image sensor from light with the first wavelengths.

Abstract: In accordance with an example embodiment a method, apparatus and computer program product are provided. The method comprises determining a plurality of first pixels having resemblance with a second pixel associated with an image based on a depth information of the image. The method further comprises replacing the second pixel by at least one first pixel of the plurality of first pixels based on a determination that the at least one first pixel is not associated with the at least one image defect.

Abstract: In an example embodiment, a method, apparatus and computer program product are provided. The method includes computing a first cost volume for a light-field image. A first depth map comprising depth information of the plurality of sub-images of the light-field image is computed based on the first cost volume. A first view image comprising reconstruction information is reconstructed based on the depth information of the plurality of sub-images. A second cost volume corresponding to the first cost volume is computed based on the reconstruction information. The second cost volume is filtered based on the first view image to generate an aggregated cost volume. A second depth map is generated based on the aggregated cost volume. The second depth map facilitates generation of a second view image that is associated with a resolution higher than a resolution of the first view image.

Abstract: An apparatus comprising: a depth map estimator configured to determine, associated with at least one visual image, a depth map comprising at least one distance value in a direction relative to an apparatus; a direction of arrival estimator configured to determine, using at least two microphones, at least one audio source signal with a direction; and an audio signal processor configured to process the at least one audio source signal based on the at least one distance value in the direction of the at least one audio source signal.

Abstract: In an example embodiment, a method, apparatus and computer program product are provided. The method includes facilitating receipt of a plurality of light-field images of a scene captured in a burst capture by a light-field camera. The method includes determining shifts between images of the plurality of light-field images, where the shifts between the images of the plurality of light-field images are associated with shake of the light-field camera while capturing the plurality of light-field images. The method includes generating a plurality of depth maps for the plurality of light-field images, and generating a set of view images of the scene based on the plurality of light-field images and the plurality of depth maps. The method includes generating a refocus image by combining the set of view images based at least on the shifts between the images of the plurality of light-field images.

Abstract: Methods and apparatuses are provided for capturing an image. A method may include determining a scene to be captured at a first resolution. The scene to be captured may be within a field of view of an image sensor. The method may further include causing capture by the image sensor of a plurality of sub-images at a second resolution. The second resolution may be less than the first resolution. Each of the plurality of sub-images may depict a portion of the scene to be captured. The method may additionally include using the plurality of sub-images to generate an output image depicting the scene to be captured at the first resolution. Corresponding apparatuses are also provided.

Abstract: In accordance with an example embodiment a method, apparatus and computer program product are provided. The method comprises determining a plurality of first pixels having resemblance with a second pixel associated with an image based on a depth information of the image. The method further comprises replacing the second pixel by at least one first pixel of the plurality of first pixels based on a determination that the at least one first pixel is not associated with the at least one image defect.

Abstract: An apparatus for generating a panoramic image(s) may include a processor and memory storing executable computer code causing the apparatus to at least perform operations including generating a panoramic image(s) based on performing registration on at least two images associated with depth map data and determining an overlap region(s) between the two images within first and second items of depth map data. The computer program code may further cause the apparatus to label the overlap region(s) within the first or second item of depth map data based on generating a virtual seam(s) connecting portions of the two images to generate a composite image. The portions correspond to image data within first and second items of depth map data. The computer program code may further cause the apparatus to blend the seam of the composite image to obtain the panoramic image. Corresponding methods and computer program products are also provided.

Abstract: In an example embodiment a method, apparatus and computer program product are provided. The method includes facilitating receipt of a light-field image, determining one or more depth levels in the light-field image and generating a plurality of images from the light-field image. The method includes determining one or more registration matrices corresponding to the one or more depth levels between an image and one or more remaining images of the plurality of images. The method includes performing a super-resolution of the image and the one or more remaining images based on the one or more registration matrices to generate a super-resolved image of the image.