Abstract: Pixels in a visual representation of an object that includes one or more perspective view images may be mapped to a standard view of the object. Based on the mapping, a portion of the object captured in the visual representation of the object may be identified. A user interface on a display device may indicate the identified object portion.

Abstract: A segmentation of an object depicted in a first visual representation may be determined. The segmentation may include for each image a first respective image portion that includes the object, a second respective image portion that includes a respective ground area located beneath the object, and a third respective image portion that includes a background area located above the second respective portion and behind the object. A second visual representation may be constructed that includes the first respective image portion and a target background image portion that replaces the third respective image portion and that is selected from a target background image based on an area of the third respective image portion relative to the respective image.

Abstract: Systems and methods for automatic generation of artificial motion blur are provided. The method includes obtaining a sequence of images of an object captured along a camera translation. Then, a multi-view interactive digital media representation (MIDMR) of the object is generated. Generating the MIDMR includes segmenting the object and then adding a blur effect to all parts of the MIDMR except for the segmented object.

Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. In particular, a multi-view interactive digital media representation (MVIDMR) of a person can be generated from live images of a person captured from a hand-held camera. Using the image data from the live images, a skeleton of the person and a boundary between the person and a background can be determined from different viewing angles and across multiple images. Using the skeleton and the boundary data, effects can be added to the person, such as wings. The effects can change from image to image to account for the different viewing angles of the person captured in each image.

Abstract: Pixels in a visual representation of an object that includes one or more perspective view images may be mapped to a standard view of the object. Based on the mapping, a portion of the object captured in the visual representation of the object may be identified. A user interface on a display device may indicate the identified object portion.

Abstract: A segmentation of an object depicted in a first visual representation may be determined. The segmentation may include for each image a first respective image portion that includes the object, a second respective image portion that includes a respective ground area located beneath the object, and a third respective image portion that includes a background area located above the second respective portion and behind the object. A second visual representation may be constructed that includes the first respective image portion and a target background image portion that replaces the third respective image portion and that is selected from a target background image based on an area of the third respective image portion relative to the respective image.

Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. In particular, a multi-view interactive digital media representation (MVIDMR) of a person can be generated from live images of a person captured from a hand-held camera. Using the image data from the live images, a skeleton of the person and a boundary between the person and a background can be determined from different viewing angles and across multiple images. Using the skeleton and the boundary data, effects can be added to the person, such as wings. The effects can change from image to image to account for the different viewing angles of the person captured in each image.

Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. In particular, a multi-view interactive digital media representation (MVIDMR) of a person can be generated from live images of a person captured from a hand-held camera. Using the image data from the live images, a skeleton of the person and a boundary between the person and a background can be determined from different viewing angles and across multiple images. Using the skeleton and the boundary data, effects can be added to the person, such as wings. The effects can change from image to image to account for the different viewing angles of the person captured in each image.

Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. In particular, a multi-view interactive digital media representation (MVIDMR) of a person can be generated from live images of a person captured from a hand-held camera. Using the image data from the live images, a skeleton of the person and a boundary between the person and a background can be determined from different viewing angles and across multiple images. Using the skeleton and the boundary data, effects can be added to the person, such as wings. The effects can change from image to image to account for the different viewing angles of the person captured in each image.

Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. In particular, a multi-view interactive digital media representation (MVIDMR) of a person can be generated from live images of a person captured from a hand-held camera. Using the image data from the live images, a skeleton of the person and a boundary between the person and a background can be determined from different viewing angles and across multiple images. Using the skeleton and the boundary data, effects can be added to the person, such as wings. The effects can change from image to image to account for the different viewing angles of the person captured in each image.

Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. In particular, a multi-view interactive digital media representation (MVIDMR) of a person can be generated from live images of a person captured from a hand-held camera. Using the image data from the live images, a skeleton of the person and a boundary between the person and a background can be determined from different viewing angles and across multiple images. Using the skeleton and the boundary data, effects can be added to the person, such as wings. The effects can change from image to image to account for the different viewing angles of the person captured in each image.

Abstract: A method and an apparatus for generating superpixels for a sequence of images. A cluster assignment generator generates a cluster assignment for a first image of the sequence of images, e.g. by clustering pixels of the first image into superpixels or by retrieving an initial cluster assignment for the first image and processing only contour pixels with regard to their cluster assignment. A label propagator initializes subsequent images based on a label propagation using backward optical flow. A contour pixel processor then processes only contour pixels with regard to their cluster assignment for subsequent images of the sequence of images.

Abstract: A method for generating superpixels for an image comprising pixels and an apparatus configured to perform the method. A clustering stage clusters the pixels into initial clusters. A determination stage then selects spatially coherent parts of the clusters and determines unconnected fragments of the clusters. Pixels of these unconnected fragments are iteratively assigned to adjacent clusters by an assignment stage using a contour evolution process.

Abstract: A method and an apparatus for life cycle management for superpixels associated to frames of a sequence of frames are described. An area occupied by a superpixel in a frame of the sequence of frames is monitored. In case the area of the superpixel becomes smaller than a specified first value, the superpixel is terminated in the later frame. In case the area of the superpixel becomes larger than a specified second value, the superpixel is split in the later frame.

Abstract: A method for generating superpixels for an image comprising pixels and an apparatus configured to perform the method. A clustering stage clusters the pixels into initial clusters. A determination stage then selects spatially coherent parts of the clusters and determines unconnected fragments of the clusters. Pixels of these unconnected fragments are iteratively assigned to adjacent clusters by an assignment stage using a contour evolution process.

Abstract: A method and an apparatus for generating superpixels for a sequence of images. A cluster assignment generator generates a cluster assignment for a first image of the sequence of images, e.g. by clustering pixels of the first image into superpixels or by retrieving an initial cluster assignment for the first image and processing only contour pixels with regard to their cluster assignment. A label propagator initializes subsequent images based on a label propagation using backward optical flow. A contour pixel processor then processes only contour pixels with regard to their cluster assignment for subsequent images of the sequence of images.

Abstract: A method and an apparatus for life cycle management for superpixels associated to frames of a sequence of frames are described. An area occupied by a superpixel in a frame of the sequence of frames is monitored. In case the area of the superpixel becomes smaller than a specified first value, the superpixel is terminated in the later frame. In case the area of the superpixel becomes larger than a specified second value, the superpixel is split in the later frame.

Abstract: A method and an apparatus for generating superpixels for a sequence of frames are presented. A feature space of the sequence of frames is separated into a color subspace and a spatial subspace. A clustering is then performed that comprises iterative assigning and updating.

Abstract: A method and an apparatus for life cycle management for superpixels associated to frames of a sequence of frames are described. An area occupied by a superpixel in a frame of the sequence of frames is monitored. In case the area of the superpixel becomes smaller than a specified first value, the superpixel is terminated in the later frame. In case the area of the superpixel becomes larger than a specified second value, the superpixel is split in the later frame.

Abstract: A method and an apparatus for life cycle management for superpixels associated to frames of a sequence of frames are described. An area occupied by a superpixel in a frame of the sequence of frames is monitored. In case the area of the superpixel becomes smaller than a specified first value, the superpixel is terminated in the later frame. In case the area of the superpixel becomes larger than a specified second value, the superpixel is split in the later frame.