摘要:
This disclosure describes techniques for coding 3D video block units. In one example, a video encoder is configured to receive one or more texture components from at least a portion of an image representing a view of three dimensional video data, receive a depth map component for at least the portion of the image, code a block unit indicative of pixels of the one or more texture components for a portion of the image and the depth map component. The coding comprises receiving texture data for a temporal instance of a view of video data, receiving depth data corresponding to the texture data for the temporal instance of the view of video data, and encapsulating the texture data and the depth data in a view component for the temporal instance of the view, such that the texture data and the depth data are encapsulated within a common bitstream.
摘要:
This disclosure describes techniques for estimating a depth of image objects for a two-dimensional (2D) view of a video presentation. For example, an initial indication of depth (e.g., an optical flow) may be determined for a 2D view. The initial indication of depth may be used to estimate global motion, e.g., motion of an observer (e.g., camera), of the 2D view. The initial indication of depth may be modified based on the estimation of global motion to create a global motion-adjusted indication of depth. The global motion-adjusted depth indication may be used to create a depth map for the 2D view, which may be used to generate an alternative view of the video presentation that may be used to display a three-dimensional (3D) video presentation.
摘要:
This disclosure describes techniques for estimating a depth of image objects for a two-dimensional (2D) view of a video presentation. For example, a plurality of feature points may be determined for a 2D view. The plurality of feature points may be used to estimate global motion, e.g., motion of an observer (e.g., camera), of the 2D view. For example, the plurality of feature points may be used to generate a global motion frame difference. The global motion frame difference may be used to create a depth map for the 2D view, which may be used to generate an alternative view of the video presentation that may be used to display a three-dimensional (3D) video presentation.
摘要:
This disclosure describes techniques for estimating a depth of image objects for a two-dimensional (2D) view of a video presentation. For example, a plurality of feature points may be determined for a 2D view. The plurality of feature points may be used to estimate global motion, e.g., motion of an observer (e.g., camera), of the 2D view. For example, the plurality of feature points may be used to generate a global motion frame difference. The global motion frame difference may be used to create a depth map for the 2D view, which may be used to generate an alternative view of the video presentation that may be used to display a three-dimensional (3D) video presentation.
摘要:
A video coding device may be configured to code a bitstream including multiple views plus depth information. Two of the views may have reduced resolutions, while a third view may have a full resolution. The third view may be predicted relative to upsampled versions of the two reduced-resolution views. Each view may include texture data and depth data, such that a view component may include a texture component and a depth component. Moreover, the texture and depth components may be arranged within an access unit according to a particular order, which may simplify component extraction from the access unit.
摘要:
This disclosure describes techniques for coding 3D video block units. In one example, a video encoder is configured to receive one or more texture components from at least a portion of an image representing a view of three dimensional video data, receive a depth map component for at least the portion of the image, code a block unit indicative of pixels of the one or more texture components for a portion of the image and the depth map component. The coding comprises receiving texture data for a temporal instance of a view of video data, receiving depth data corresponding to the texture data for the temporal instance of the view of video data, and encapsulating the texture data and the depth data in a view component for the temporal instance of the view, such that the texture data and the depth data are encapsulated within a common bitstream.
摘要:
This disclosure describes techniques for estimating a depth of image objects for a two-dimensional (2D) view of a video presentation. For example, an initial indication of depth (e.g., an optical flow) may be determined for a 2D view. The initial indication of depth may be used to estimate global motion, e.g., motion of an observer (e.g., camera), of the 2D view. The initial indication of depth may be modified based on the estimation of global motion to create a global motion-adjusted indication of depth. The global motion-adjusted depth indication may be used to create a depth map for the 2D view, which may be used to generate an alternative view of the video presentation that may be used to display a three-dimensional (3D) video presentation.
摘要:
This disclosure describes techniques for generating depth maps for video units, such as video frames or slices video frames. The techniques may be performed by a video encoder in order to convert two-dimensional (2D) video to three-dimensional (3D) video. The techniques may alternatively be performed by a video decoder in order to convert received 2D video to 3D video. The techniques may use a combination of motion and color considerations in the depth map generation process.
摘要:
Stereoscopic video data encoded according to a full resolution frame-compatible stereoscopic vide coding process. Such stereoscopic video data consists of a right view and a left that are encoded in half resolution versions in an interleaved base layer and an interleaved enhancement layer. When decoded, the right view and left view are filtered according to two sets of filter coefficients, one set for the left view and one set for the right view. The sets of filter coefficients are generated by an encoder by comparing the original left and right views to decoded versions of the left and right views.
摘要:
A video coding device may be configured to code a bitstream including multiple views plus depth information. Two of the views may have reduced resolutions, while a third view may have a full resolution. The third view may be predicted relative to upsampled versions of the two reduced-resolution views. Each view may include texture data and depth data, such that a view component may include a texture component and a depth component. Moreover, the texture and depth components may be arranged within an access unit according to a particular order, which may simplify component extraction from the access unit.