Abstract: A method, computer program product, and computer system for identifying a first portion of a facial image in a first image, wherein the first portion includes noise. A corresponding portion of the facial image is identified in a second image, wherein the corresponding portion includes less noise than the first portion. One or more filter parameters of the first portion are determined based upon, at least in part, the first portion and the corresponding portion. At least a portion of the noise from the first portion is smoothed based upon, at least in part, the one or more filter parameters. At least a portion of face specific details from the corresponding portion is added to the first portion.

Abstract: A computer-implemented method, computer program product, and computing system is provided for interacting with images having similar content. In an embodiment, a method may include identifying a plurality of photographs as including a common characteristic. The method may also include generating a flipbook media item including the plurality of photographs. The method may further include associating one or more interactive control features with the flipbook media item.

Abstract: An exemplar dictionary is built from exemplars of digital content for determining predictor blocks for encoding and decoding digital content. The exemplar dictionary organizes the exemplars as clusters of similar exemplars. Each cluster is mapped to a label. Machine learning techniques are used to generate a prediction model for predicting a label for an exemplar. The exemplar dictionary is used to encode digital content. Clusters of exemplars are obtained by applying a prediction model to a target block of digital content for encoding. A predictor block is selected for encoding the target block based on frequency of occurrence of exemplars in the clusters. The target block is encoded using the predictor block.

Abstract: An image processing server performs haze-removal from images. Global atmospheric light is estimated and an initial transmission value is estimated. In one embodiment, a solver is applied to an objective function to recover a scene radiance value based on the estimated atmospheric light and estimated transmission value. The scene radiance value is used to construct an image without haze. In a simplified method that avoids using a solver, bilateral filtering is performed on the transmission image in order to construct an image without haze.

Abstract: Methods and systems for rolling shutter removal are described. A computing device may be configured to determine, in a frame of a video, distinguishable features. The frame may include sets of pixels captured asynchronously. The computing device may be configured to determine for a pixel representing a feature in the frame, a corresponding pixel representing the feature in a consecutive frame; and determine, for a set of pixels including the pixel in the frame, a projective transform that may represent motion of the camera. The computing device may be configured to determine, for the set of pixels in the frame, a mixture transform based on a combination of the projective transform and respective projective transforms determined for other sets of pixels. Accordingly, the computing device may be configured to estimate a motion path of the camera to account for distortion associated with the asynchronous capturing of the sets of pixels.

Abstract: An image processing module performs efficient image enhancement according to a multi-scale energy minimization process. One or more input images are progressively downsampled to generate a pyramid of downsampled images of varying resolution. Starting with the coarsest downsampled image, a label map is generated that maps output pixel positions to pixel positions in the downsampled input images. The label map is then progressively upsampled. At each upsampling stage, the labels are refined according to an energy function configured to produce the desired enhancements. Using the multi-scale energy minimization, the image processing module enhances image via hole-filling and/or super-resolution.

Abstract: Clustering algorithms such as k-means clustering algorithm are used in applications that process entities with spatial and/or temporal characteristics, for example, media objects representing audio, video, or graphical data. Feature vectors representing characteristics of the entities are partitioned using clustering methods that produce results sensitive to an initial set of cluster seeds. The set of initial cluster seeds is generated using principal component analysis of either the complete feature vector set or a subset thereof. The feature vector set is divided into a desired number of initial clusters and a seed determined from each initial cluster.

Abstract: Methods and systems for video retargeting and view selection using motion saliency are described. Salient features in multiple videos may be extracted. Each video may be retargeted by modifying the video to preserve the salient features. A crop path may be estimated and applied to a video to retarget each video and generate a modified video preserving the salient features. An action score may be assigned to portions or frames of each modified video to represent motion content in the modified video. Selecting a view from one of the given modified videos may be formulated as an optimization subject to constraints. An objective function for the optimization may include maximizing the action score. This optimization may also be subject to constraints to take into consideration optimal transitioning from a view from a given video to another view from another given video, for example.

Abstract: A video is segmented to produce volumetric video regions. Descriptors are created for the video regions. A region graph is created for the video, where the region graph has weighted edges incident to video regions and the weight of an edge is calculated responsive to the descriptors of the video regions incident to the edge. The region graph is segmented responsive to the weights of the edges incident to the video regions to produce a new region graph having new volumetric video regions comprised of merged video regions of the first region graph. The descriptions of the region graphs are stored in a data storage.

Abstract: An image processing server enhances an original image using image data from other images. The server generates global descriptors of a set of received images and creates an image data structure therefrom. The server also identifies a set of patches for each of the received images, generates descriptors of the patches, and generates a patch data structure therefrom. The image processing system identifies a patch in an original image for which enhancement is desired. The image processing server uses a global descriptor of the original image to search the image data structure for a set of related images that are visually similar to the original image. The image processing server uses a patch descriptor of the patch for which enhancement is desired to search the patch data structures for the related images to identify a set of patches that are visually similar to the patch in the original image.

Abstract: Methods and systems for video retargeting and view selection using motion saliency are described. Salient features in multiple videos may be extracted. Each video may be retargeted by modifying the video to preserve the salient features. A crop path may be estimated and applied to a video to retarget each video and generate a modified video preserving the salient features. An action score may be assigned to portions or frames of each modified video to represent motion content in the modified video. Selecting a view from one of the given modified videos may be formulated as an optimization subject to constraints. An objective function for the optimization may include maximizing the action score. This optimization may also be subject to constraints to take into consideration optimal transitioning from a view from a given video to another view from another given video, for example.

Abstract: A covariance matrix associated for a set of spatial and/or temporal sub-portions of a media object is populated based on a lookup table of relative displacements and sums of covariance values generated from pairs of data elements in the media object. The lookup table is generated in linear time, providing an efficient method of generating the covariance matrix.

Abstract: An image processing system enhances the resolution of an original image using higher-resolution image data from other images. The image processing system defines a plurality of overlapping partitions for the original image, each partition defining a set of non-overlapping site patches. During an optimization phase, the system identifies, for site patches of the original images, label patches within related images that are of most relevance. During a rendering phase independent of the optimization phase, an output image with enhanced resolution is synthesized by substituting, for site patches of the original image, the identified relevant label patches from the related images.

Abstract: Methods and systems for processing a video for stabilization and retargeting are described. A recorded video may be stabilized by removing shake introduced in the video, and a video may be retargeted by modifying the video to fit to a different aspect ratio. Constraints can be imposed that require a modified video to contain pixels from the original video and/or to preserve salient regions. In one example, a video may be processed to estimate an original path of a camera that recorded the video, to estimate a new camera path, and to recast the video from the original path to the new camera path. To estimate a new camera path, a virtual crop window can be designated. A difference transformation between the original and new camera path can be applied to the video using the crop window to recast the recorded video from the smooth camera path.

Abstract: An exemplar dictionary is built from example image blocks for determining predictor blocks for encoding and decoding images. The exemplar dictionary comprises a hierarchical organization of example image blocks. The hierarchical organization of image blocks is obtained by clustering a set of example image blocks, for example, based on k-means clustering. Performance of clustering is improved by transforming feature vectors representing the image blocks to fewer dimensions. Principal component analysis is used for determining feature vectors with fewer dimensions. The clustering performed at higher levels of the hierarchy uses fewer dimensions of feature vectors compared to lower levels of hierarchy. Performance of clustering is improved by processing only a sample of the image blocks of a cluster. The clustering performed at higher levels of the hierarchy uses lower sampling rates as compared to lower levels of hierarchy.

Abstract: Methods and systems for processing a video for stabilization are described. A recorded video may be stabilized by removing at least a portion of shake introduced in the video. An original camera path for a camera used to record the video may be determined. A crop window size may be selected and a crop window transform may accordingly be determined. The crop window transform may describe a transform of the original camera path to a modified camera path that is smoother than the original camera path. A smoothness metric indicative of a degree of smoothness of the modified path may be determined. Based on a comparison of the smoothness metric to a predetermined threshold, for example, the crop window transform may be applied to the original video to obtain a stabilized modified video.

Abstract: Compression of an image is performed based on prediction of target blocks of an image from candidate source blocks of the image. Heuristics are used for identifying the candidate source blocks, for example, source blocks are selected from within a cluster of similar blocks obtained by K-means clustering. For each target block, a region adjacent to the target block is identified and a set of candidate source blocks along with candidate source regions adjacent to the candidate source blocks are identified. The candidate source regions are ranked based on the differences between the candidate source regions and the target source region. Each candidate source block is described using its rank and residual information describing differences between the candidate source block and the target block. The candidate source block that can be described using a minimum amount of information is selected for predicting the target block.

Abstract: Methods and systems for processing an image to create an object model are disclosed. In accordance with one embodiment, each segment of the image is assigned to a respective bin of a bounding box. For each bin of the bounding box, the value of a feature for the bin is computed based on the values of that feature for each of the segments assigned to the bin. An object model is then created based on the values of the feature for the bin.

Abstract: An image processing system enhances the resolution of an original image using higher-resolution image data from other images. The image processing system defines a plurality of overlapping partitions for the original image, each partition defining a set of non-overlapping site patches. During an optimization phase, the system identifies, for site patches of the original images, label patches within related images that are of most relevance. During a rendering phase independent of the optimization phase, an output image with enhanced resolution is synthesized by substituting, for site patches of the original image, the identified relevant label patches from the related images.

Abstract: An image comprising varying illumination is selected. Instances of a repeating pattern in the image is determined. Illumination values for pixels at locations within instances of the repeating pattern are calculated responsive to pixel intensities of pixels at corresponding locations in other instances of the repeating pattern. The varying illumination is removed form the image responsive to the illumination values.