The present invention relates to a system and method for capturing video of a real-world scene over a field of view that may exceed the field of view of a user, manipulating the captured video, and then stereoscopically displaying the manipulated image to the user in a head mounted display to create a virtual environment having length, width, and depth in the image. By capturing and manipulating video for a field of view that exceeds the field of view of the user, the system and method can quickly respond to movement by the user to update the display allowing the user to look and pan around, i.e., navigate, inside the three-dimensional virtual environment.

The present invention relates to a system and method for capturing video of a real-world scene over a field of view that may exceed the field of view of a user, manipulating the captured video, and then stereoscopically displaying the manipulated image to the user in a head mounted display to create a virtual environment having length, width, and depth in the image. By capturing and manipulating video for a field of view that exceeds the field of view of the user, the system and method can quickly respond to movement by the user to update the display allowing the user to look and pan around, i.e., navigate, inside the three-dimensional virtual environment.

An information display apparatus 400 obtains information about a plurality of apparatuses for obtaining a plurality of images captured from a plurality of directions for use in generating a virtual viewpoint image corresponding to a specified viewpoint. Furthermore, the information display apparatus 400 identifies an apparatus in an abnormal state among the plurality of apparatuses based on the obtained information. The information display apparatus 400 then causes the display unit 404 to display information indicating one or a plurality of apparatuses, among the plurality of apparatuses, that are in a predetermined relationship with the apparatus in the abnormal state.

State information indicating states of a plurality of imaging apparatuses 100-x used for generating a virtual viewpoint image is acquired. At least one image type is determined from a plurality of image types indicating display formats of displaying the states of the plurality of imaging apparatuses 100-x based on the state information. Based on the determined image type, the states of the plurality of imaging apparatuses 100-x are displayed.

State information indicating states of a plurality of imaging apparatuses 100-x used for generating a virtual viewpoint image is acquired. At least one image type is determined from a plurality of image types indicating display formats of displaying the states of the plurality of imaging apparatuses 100-x based on the state information. Based on the determined image type, the states of the plurality of imaging apparatuses 100-x are displayed.

A video transmission method that includes predicting, from a texture picture or a depth picture of an anchor viewing position, a picture for a target viewing position on the basis of target viewing position information and processing a prediction error with respect to the predicted picture on the basis of a source picture of the target viewing position. An error-prone region map is generated on the basis of the predicted picture and the source picture. The video transmission method also includes patch packing the prediction error-processed picture on the basis of the error-prone region map and encoding the packed patch on the basis of the texture picture or the depth picture of the anchor viewing position.

A video transmission method that includes predicting, from a texture picture or a depth picture of an anchor viewing position, a picture for a target viewing position on the basis of target viewing position information and processing a prediction error with respect to the predicted picture on the basis of a source picture of the target viewing position. An error-prone region map is generated on the basis of the predicted picture and the source picture. The video transmission method also includes patch packing the prediction error-processed picture on the basis of the error-prone region map and encoding the packed patch on the basis of the texture picture or the depth picture of the anchor viewing position.

The present invention provides a user with a user interface for enabling the user to efficiently perform an operation for generating a virtual viewpoint image for each imaging target subject to be imaged by a plurality of imaging apparatuses. An event information acquisition unit acquires information about an event subjected to virtual viewpoint image generation, and transmits the acquired event information to a user interface (UI) determination unit. The UI determination unit determines a UI to be generated by a UI generation unit based on the event information transmitted from the event information acquisition unit. The UI generation unit generates the UI determined by the UI determination unit. The user performs an input operation for generating a virtual viewpoint image according to the UI generated by the UI generation unit.

A Free Viewpoint Video (FVV) generation and interaction method based on a deep Convolutional Neural Network (CNN) includes the steps of: acquiring multi-viewpoint data of a target scene by a synchronous shooting system with a multi-camera array arranged accordingly to obtain groups of synchronous video frame sequences from a plurality of viewpoints, and rectifying baselines of the sequences at pixel level in batches; extracting, by encoding and decoding network structures, features of each group of viewpoint images input into a designed and trained deep CNN model, to obtain deep feature information of the scene, and combining the information with the input images to generate a virtual viewpoint image between each group of adjacent physical viewpoints at every moment; and synthesizing all viewpoints into frames of the FVV based on time and spatial position of viewpoints by stitching matrices. The method eliminates the need for camera rectification and depth image calculation.

A Free Viewpoint Video (FVV) generation and interaction method based on a deep Convolutional Neural Network (CNN) includes the steps of: acquiring multi-viewpoint data of a target scene by a synchronous shooting system with a multi-camera array arranged accordingly to obtain groups of synchronous video frame sequences from a plurality of viewpoints, and rectifying baselines of the sequences at pixel level in batches; extracting, by encoding and decoding network structures, features of each group of viewpoint images input into a designed and trained deep CNN model, to obtain deep feature information of the scene, and combining the information with the input images to generate a virtual viewpoint image between each group of adjacent physical viewpoints at every moment; and synthesizing all viewpoints into frames of the FVV based on time and spatial position of viewpoints by stitching matrices. The method eliminates the need for camera rectification and depth image calculation.