Abstract: The invention describes a method for applying a geometric warp to the light field capture of a 3D scene, consisting of several views of the scene taken from different viewpoints. The warp is specified as a set of (source point, target point) positional constraints on a subset of the views. These positional constraints are propagated to all the views and a warped image is generated for each view, in such a way that these warped images are geometrically consistent in 3D across the views.

Abstract: A method for sculpting a template 3D model comprises receiving (12) a deformation to be applied to the template 3D model. In response to the received deformation, at least one action is executed (13) on at least the template 3D model or a reference 3D model. Such an action uses a set of dependency data representing interrelations between the reference 3D model and the template 3D model, the action(s) providing a user with a corrective feedback on the deformation to be applied, that feedback being adapted to enable the user to avoid exceeding deformation bounds in applying the deformation. The user sculpting the template 3D model can thus be guided during the modeling process.

Abstract: A method and an apparatus for displaying light field video data are described. A receiving unit of the apparatus receives light field video data including a plurality of light field video sequences. Each light field video frames of of the light field video sequences has multiple selectable viewpoints. A light field video frame is provided by an operation unit and displayed on a display device with a first viewpoint. An input unit receives an input indicating a viewpoint different from the first viewpoint. The displayed light field video frame is then displayed with the indicated viewpoint. In one embodiment, two light field video frames of two light field video sequences are displayed respectively in main and side windows on the display device.

Abstract: The disclosure relates to a method for classifying an object of a current image, a plurality of first landmarks representative of the shape of the object being associated with the current image, a first unique identifier being associated with each first landmark. According to the disclosure, the method includes, for at least a first landmark, a step of obtaining at least a first descriptor describing an area of the current image having the at least first selected landmark. Then, the first landmark is selected according to its first identifier, and when its first identifier corresponds to a second identifier of a second landmark, a second descriptor is used in a classifier for classifying the object. Finally, the method determines information representative of confidence of the shape according to the first descriptor and according to weighting information associated with the second descriptor.

Abstract: A method for processing an image of pixels is described. The method includes determining a plurality of features representative of the image, obtaining both information representative of a probability of presence of an object in the image and information representative of a shape of the object by implementing a unique multivariate regression applied to at least a part of the features.

Abstract: The disclosure relates to a method for determining the shape (St) of an object represented in a current image, a plurality of landmarks being associated with the object. According to the disclosure, the method includes determining a plurality of features (Ft) representative of the current image, and the features being determined from at least a part of the plurality of landmarks. The method further obtains information (St) representative of the shape of the object by using at least one parameter (Pt) representative of an estimation of the pose of the object in the current image, the at least one parameter being obtained by implementing a multivariate regression applied to at least a part of the set of features.

Abstract: In a method for consistently editing stereographs in warping at least part of a virtual 3D scene, a set of positional constraints is associated with a source and a target position of at least one constraint point in at least one specified depth layer of each of two specified stereographic images. The source and target positions in both images are respectively associated with semantic source and target point in the 3D scene. Those images are warped by applying these positional constraints for each of the specified depth layer and a warped stereograph is generated, comprising the two warped images for the specified depth layer.

Abstract: A method of generating a first image, the method including, for each second image of a set of second images representative of an object, obtaining an information representative of a shape of the object; clustering the second images into a plurality of clusters according to the information; for each cluster of the plurality of clusters, generating the first image using the information associated with each second image of the cluster, the first image being representative of the cluster. A corresponding device is also recited.

Abstract: A method and an electronic device for object tracking in a sequence of light-field captures. A data acquisition unit acquires a sequence of light-field captures, wherein each light-field capture comprises a plurality of views. A feature determining unit determines features of an initial visual appearance model for an object of interest in a reference view of a first light-field capture. A feature matching unit matches the features in the reference view and in the further views of the first light-field capture. A feature discarding unit discards features that cannot be well matched in all views of the first light-field capture. An appearance model building unit builds an updated visual appearance model for the object of interest based on the remaining features. Finally, a movement tracking unit tracks the movement of the object of interest in the sequence of light-field captures using the visual appearance model.

Abstract: The application concerns a method for transmitting video data in a data stream and associated metadata, said metadata representing associated video data structure. The method comprises the steps of—determining the structure of the video data, —splitting said structure into chunks in an incremental manner, —transmitting said chunks in the data stream at time intervals before the video data it is related to. The application concerns also a method for transmitting fingerprint information associated with video data into a video data stream. The method comprises the steps of: —determining fingerprint associated with at least one frame of said video data, —inserting at least a message into the video stream comprising said fingerprint information.

Abstract: A method and device for synthesizing a first face in a first image, by determining a first occluded part of the first face that is occluded by an occluding object; determining a first visible part of the first face from the first occluded part; calculating first attributes representative of the first visible part; obtaining first parameters representative of an appearance of the first face by applying a regressor to the first attributes, the regressor modelling a correlation between second attributes representative of second visible parts of a plurality of second faces in second images and second parameters representative of an appearance model of the plurality of second faces; and synthesizing the first face using the first parameters.

Abstract: A method for shooting a performance making use of umanned aerial vehicles, such as drones for example, to provide the physical markers that are needed to give a physical actor indications on the positioning of virtual elements to be inserted later in the scene, and with which s/he needs to interact.

Abstract: The disclosure relates to a method for determining the shape (St) of an object represented in a current image, a plurality of landmarks being associated with the object. According to the disclosure, the method includes determining a plurality of features (Ft) representative of the current image, and the features being determined from at least a part of the plurality of landmarks. The method further obtains information (St) representative of the shape of the object by using at least one parameter (Pt) representative of an estimation of the pose of the object in the current image, the at least one parameter being obtained by implementing a multivariate regression applied to at least a part of the set of features.

Abstract: The disclosure relates to a method for classifying an object of a current image, a plurality of first landmarks representative of the shape of the object being associated with the current image, a first unique identifier being associated with each first landmark. According to the disclosure, the method includes, for at least a first landmark, a step of obtaining at least a first descriptor describing an area of the current image having the at least first selected landmark. Then, the first landmark is selected according to its first identifier, and when its first identifier corresponds to a second identifier of a second landmark, a second descriptor is used in a classifier for classifying the object. Finally, the method determines information representative of confidence of the shape according to the first descriptor and according to weighting information associated with the second descriptor.

Abstract: A method for processing an image of pixels is described. The method includes determining a plurality of features representative of the image, obtaining both information representative of a probability of presence of an object in the image and information representative of a shape of the object by implementing a unique multivariate regression applied to at least a part of the features.

Abstract: A method and an apparatus for displaying light field video data are described. A receiving unit of the apparatus receives light field video data including a plurality of light field video sequences. Each light field video frames of of the light field video sequences has multiple selectable viewpoints. A light field video frame is provided by an operation unit and displayed on a display device with a first viewpoint. An input unit receives an input indicating a viewpoint different from the first viewpoint. The displayed light field video frame is then displayed with the indicated viewpoint. In one embodiment, two light field video frames of two light field video sequences are displayed respectively in main and side windows on the display device.

Abstract: A method and an electronic device for object tracking in a sequence of light-field captures. A data acquisition unit acquires a sequence of light-field captures, wherein each light-field capture comprises a plurality of views. A feature determining unit determines features of an initial visual appearance model for an object of interest in a reference view of a first light-field capture. A feature matching unit matches the features in the reference view and in the further views of the first light-field capture. A feature discarding unit discards features that cannot be well matched in all views of the first light-field capture. An appearance model building unit builds an updated visual appearance model for the object of interest based on the remaining features. Finally, a movement tracking unit tracks the movement of the object of interest in the sequence of light-field captures using the visual appearance model.

Abstract: The invention relates to a method for selection of a first object in a first virtual environment, the first object being represented in the first environment with a size of value less than a threshold value. According to an exemplary embodiment, in order to make the selection of the first object more convivial, the method includes steps for: estimating a direction associated with a pointing gesture of a user, determining a second object according to the estimated direction, the second object having a size of value greater than the threshold value, and selecting of the first object according to the second determined object. The invention also relates to a multimedia terminal adapted for the implementation of the method for selection.

Abstract: A method of displaying a neutral facial expression in a paused video includes analyzing contiguous frames of a video to find neutral facial expressions and associating one of the neutral facial expression frames with each frame in the video. Upon reception of a pause instruction, synthesizing a set of frames that transition from the associated neutral expression frame to a pause frame. The synthesized frames are played in reverse, whereby the played frames transition from the pause frame to the associated neutral expression frame. Thus, the neutral facial expression frame is displayed on the video player while the video is paused instead of displaying the normal pause frame.

Abstract: A method for controlling a path of a rotary-wing drone wherein said method comprises: Establishing a first-order temporal relation between flight control parameters and flight dynamics for said rotary-wing drone comprising: An Explicit Discrete Time-Variant State-Space Representation of a translation control of said rotary-wing drone; An Explicit Discrete Time-Variant State-Space Representation of a course control of said rotary-wing drone; Controlling the path of said rotary-wing drone by: Estimating a course of said rotary-wing drone on the basis of said Explicit Discrete Time-Variant State-Space Representation of a course control of said rotary-wing drone; Estimating a position of said rotary-wing drone on the basis of said Explicit Discrete Time-Variant State-Space Representation of a translation control of said rotary-wing drone; said steps of estimating being performed independently.