Abstract: Estimating a pose of an articulated 3D object model (4) by a computer is done by •obtaining a sequence of source images (10) and therefrom corresponding source image segments (13) with objects (14) separated from the image background; •matching such a sequence (51) with sequences (52) of reference silhouettes (13?), determining one or more selected sequences of reference silhouettes (13?) forming a best match; •for each of these selected sequences of reference silhouettes (13?), retrieving a reference pose that is associated with one of the reference silhouettes (13?); and •computing an estimate of the pose of the articulated object model (4) from the retrieved reference pose or poses. The result of these steps is an initial pose estimate, which then can be used in further steps, for example, for maintaining local consistency between pose estimates from consecutive frames, and global consistency over a longer sequence of frames.

Abstract: A computer-implemented method for estimating a pose of an articulated object model that is a computer based 3D model of a real world object observed by one or more source cameras, including the steps of obtaining a source image from a video stream; processing the source image to extract a source image segment maintaining, in a database, a set of reference silhouettes, each being associated with an articulated object model and a corresponding reference pose; comparing the source image segment to the reference silhouettes and selecting reference silhouettes by taking into account, for each reference silhouette, a matching error that indicates how closely the reference silhouette matches the source image segment retrieving the corresponding reference poses of the articulated object models; and computing an estimate of the pose of the articulated object model from the reference poses of the selected reference silhouettes.

Abstract: Estimating a pose of an articulated 3D object model (4) by a computer is done by •obtaining a sequence of source images (10) and therefrom corresponding source image segments (13) with objects (14) separated from the image background; •matching such a sequence (51) with sequences (52) of reference silhouettes (13?), determining one or more selected sequences of reference silhouettes (13?) forming a best match; •for each of these selected sequences of reference silhouettes (13?), retrieving a reference pose that is associated with one of the reference silhouettes (13?); and •computing an estimate of the pose of the articulated object model (4) from the retrieved reference pose or poses. The result of these steps is an initial pose estimate, which then can be used in further steps, for example, for maintaining local consistency between pose estimates from consecutive frames, and global consistency over a longer sequence of frames.

Abstract: A method of processing image data includes providing an image sequence such as a video sequence, or a camera transition, identifying a region-of-interest in at least one image of the image sequence, defining a transition region around the region-of-interest and defining a remaining portion of the image to be a default region or background region, applying different image effects to the region-of-interest, the transition region and the background region.

Abstract: What is disclosed is a computer-implemented image-processing system and method for the automatic generation of video sequences that can be associated with a televised event. The methods can include the steps of: Defining a reference keyframe from a reference view from a source image sequence; From one or more keyframes, automatically computing one or more sets of virtual camera parameters; Generating a virtual camera flight path, which is described by a change of virtual camera parameters over time, and which defines a movement of a virtual camera and a corresponding change of a virtual view; and Rendering and storing a virtual video stream defined by the virtual camera flight path.

Abstract: What is disclosed is a computer-implemented image-processing system and method for the automatic generation of video sequences that can be associated with a televised event. The methods can include the steps of: Defining a reference keyframe from a reference view from a source image sequence; From one or more keyframes, automatically computing one or more sets of virtual camera parameters; Generating a virtual camera flight path, which is described by a change of virtual camera parameters over time, and which defines a movement of a virtual camera and a corresponding change of a virtual view; and Rendering and storing a virtual video stream defined by the virtual camera flight path.

Abstract: Using photographic flash for candid shots often results in an unevenly lit scene, in which objects in the back appear dark. A spatially adaptive photographic flash (100) is disclosed, in which the intensity of illumination (21, 23) varies depending on the depth and reflectivity (30, 101) of features in the scene. Adaption to changes in depth are used in a single-shot method. Adaption to changes in reflectivity are used in a multishot method. The single-shot method requires only a depth image (30), whereas the multi-shot method requires at least one color image (40) in addition to the depth data (30).

Abstract: A computer-implemented method for estimating a pose of an articulated object model (4), wherein the articulated object model (4) is a computer based 3D model (1) of a real world object (14) observed by one or more source cameras (9), and wherein the pose of the articulated object model (4) is defined by the spatial location of joints (2) of the articulated object model (4), comprises the steps of obtaining a source image (10) from a video stream; processing the source image (10) to extract a source image segment (13); maintaining, in a database, a set of reference silhouettes, each being associated with an articulated object model (4) and a corresponding reference pose; comparing the source image segment (13) to the reference silhouettes and selecting reference silhouettes by taking into account, for each reference silhouette, a matching error that indicates how closely the reference silhouette matches the source image segment (13) and/or a coherence error that indicates how much the reference pose is con

Abstract: Using photographic flash for candid shots often results in an unevenly lit scene, in which objects in the back appear dark. A spatially adaptive photographic flash (100) is disclosed, in which the intensity of illumination (21, 23) varies depending on the depth and reflectivity (30, 101) of features in the scene. Adaption to changes in depth are used in a single-shot method. Adaption to changes in reflectivity are used in a multishot method. The single-shot method requires only a depth image (30), whereas the multi-shot method requires at least one color image (40) in addition to the depth data (30).

Abstract: A method constructs three-dimensional (3D) models of a scene from a set of two-dimensional (2D) input images. The 3D model can then be used to reconstruct the scene from arbitrary viewpoints. A user segments and labels a set of corresponding polygonal regions in each image using conventional photo-editing tools. The invention constructs the model so that the model has a maximum volume that is consistent with the set of labeled regions in the input images. The method according to the invention directly constructs the polygonal model.

Abstract: A method models a three-dimensional object by first acquiring alpha mattes of the object for multiple viewpoints. The alpha mattes are then projected onto a surface hull completely enclosing the object to construct an opacity hull storing opacity values of the surface of the object. The object is illuminated for various lighting conditions while images are acquired. The images are projected onto the opacity hull to render the object under arbitrary lighting conditions for arbitrary viewpoints.

Abstract: A method constructs three-dimensional (3D) models of a scene from a set of two-dimensional (2D) input images. The 3D model can then be used to reconstruct the scene from arbitrary viewpoints.

Abstract: A method models a three-dimensional object by first acquiring alpha mattes of the object for multiple viewpoints. The alpha mattes are then projected onto a surface hull completely enclosing the object to construct an opacity hull storing opacity values of the surface of the object. The object is illuminated for various lighting conditions while images are acquired. The images are projected onto the opacity hull to render the object under arbitrary lighting conditions for arbitrary viewpoints.