Abstract: A video coding device may be configured to periodically select the frame packing configuration (e.g., face layout and/or face rotations parameters) associated with a RAS. The device may receive a plurality of pictures, which may each comprise a plurality of faces. The pictures may be grouped into a plurality of RASs. The device may select a frame packing configuration with the lowest cost for a first RAS. For example, the cost of a frame packing configuration may be determined based on the first picture of the first RAS. The device may select a frame packing configuration for a second RAS. The frame packing configuration for the first RAS may be different than the frame packing configuration for the second RAS. The frame packing configuration for the first RAS and the frame packing configuration for the second RAS may be signaled in the video bitstream.

Abstract: Systems, methods, and instrumentalities are disclosed for performing horizontal geometry padding on a current sample based on receiving a wraparound enabled indication that indicates whether a horizontal wraparound motion compensation is enabled. If the horizontal wraparound motion compensation is enabled based on the wraparound enabled indication, a video coding device may determine a reference sample wraparound offset of a current sample in a picture. The reference sample wraparound offset may indicate a face width of the picture. The video coding device may determine a reference sample location for the current sample based on the reference sample wraparound offset, a picture width of the picture, and a current sample location. The video coding device may predict the current sample based on the reference sample location in a horizontal direction. Repetitive padding or clipping may be used in the vertical direction.

Abstract: Systems, methods, and instrumentalities are disclosed for motion vector clipping when affine motion mode is enabled for a video block. A video coding device may determine that an affine mode for a video block is enabled. The video coding device may determine a plurality of control point affine motion vectors associated with the video block. The video coding device may store the plurality of clipped control point affine motion vectors for motion vector prediction of a neighboring control point affine motion vector. The video coding device may derive a sub-block motion vector associated with a sub-block of the video block, clip the derived sub-block motion vector, and store it for spatial motion vector prediction or temporal motion vector prediction. For example, the video coding device may clip the derived sub-block motion vector based on a motion field range that may be based on a bit depth value.

Abstract: A coding device (e.g., that may be or may include encoder and/or decoder) may receive a frame-packed picture of 360-degree video. The coding device may identify a face in the frame-packed picture that the current block belongs to. The coding device may determine that a current block is located at a boundary of the face that the current block belongs to. The coding device may identify multiple spherical neighboring blocks of the current block. The coding device may identify a cross-face boundary neighboring block. The coding device may identify a block in the frame-packed picture that corresponds to the cross-face boundary neighboring block. The coding device may determine whether to use the identified block to code the current block based on availability of the identified block. The coding device may code the current block based on the determination to use the identified block.

Abstract: Systems, methods, and instrumentalities are disclosed for discontinuous face boundary filtering for 360-degree video coding. A face discontinuity may be filtered (e.g., to reduce seam artifacts) in whole or in part, for example, using coded samples or padded samples on either side of the face discontinuity. Filtering may be applied, for example, as an in-loop filter or a post-processing step. 2D positional information related to two sides of the face discontinuity may be signaled in a video bitstream so that filtering may be applied independent of projection formats and/or frame packing techniques.

Abstract: Systems, methods, and instrumentalities are disclosed for motion vector clipping when affine motion mode is enabled for a video block. A video coding device may determine that an affine mode for a video block is enabled. The video coding device may determine a plurality of control point affine motion vectors associated with the video block. The video coding device may store the plurality of clipped control point affine motion vectors for motion vector prediction of a neighboring control point affine motion vector. The video coding device may derive a sub-block motion vector associated with a sub-block of the video block, clip the derived sub-block motion vector, and store it for spatial motion vector prediction or temporal motion vector prediction. For example, the video coding device may clip the derived sub-block motion vector based on a motion field range that may be based on a bit depth value.

Abstract: Coding techniques for 360-degree video are described. An encoder selects a projection format and maps the 360-degree video to a 2D planar video using the selected projection format. The encoder encodes the 2D planar video in a bitstream and further signals, in the bitstream, parameters identifying the projection format. The parameters identifying the projection format may be signaled in a video parameter set, sequence parameter set, and/or picture parameter set of the bitstream. Different projection formats that may be signaled include formats using geometries such as equirectangular, cubemap, equal-area, octahedron, icosahedron, cylinder, and user-specified polygon. Other parameters that may be signaled include different arrangements of geometric faces or different encoding quality for different faces. Corresponding decoders are also described. In some embodiments, projection parameters may further include relative geometry rotation parameters that define an orientation of the projection geometry.

Abstract: Systems, methods, and instrumentalities are disclosed for performing horizontal geometry padding on a current sample based on receiving a wraparound enabled indication that indicates whether a horizontal wraparound motion compensation is enabled. If the horizontal wraparound motion compensation is enabled based on the wraparound enabled indication, a video coding device may determine a reference sample wraparound offset of a current sample in a picture. The reference sample wraparound offset may indicate a face width of the picture. The video coding device may determine a reference sample location for the current sample based on the reference sample wraparound offset, a picture width of the picture, and a current sample location. The video coding device may predict the current sample based on the reference sample location in a horizontal direction. Repetitive padding or clipping may be used in the vertical direction.

Abstract: The techniques described herein relate to computerized methods and apparatuses for detecting objects in an image. The techniques described herein further relate to computerized methods and apparatuses for detecting one or more objects using a pre-trained machine learning model and one or more other machine learning models that can be trained in a field training process. The pre-trained machine learning model may be a deep machine learning model.

Abstract: Systems, methods, and instrumentalities are disclosed for motion vector clipping when affine motion mode is enabled for a video block. A video coding device may determine that an affine mode for a video block is enabled. The video coding device may determine a plurality of control point affine motion vectors associated with the video block. The video coding device may store the plurality of clipped control point affine motion vectors for motion vector prediction of a neighboring control point affine motion vector. The video coding device may derive a sub-block motion vector associated with a sub-block of the video block, clip the derived sub-block motion vector, and store it for spatial motion vector prediction or temporal motion vector prediction. For example, the video coding device may clip the derived sub-block motion vector based on a motion field range that may be based on a bit depth value.

Abstract: A video coding device may be configured to periodically select the frame packing configuration (e.g., face layout and/or face rotations parameters) associated with a RAS. The device may receive a plurality of pictures, which may each comprise a plurality of faces. The pictures may be grouped into a plurality of RASs. The device may select a frame packing configuration with the lowest cost for a first RAS. For example, the cost of a frame packing configuration may be determined based on the first picture of the first RAS. The device may select a frame packing configuration for a second RAS. The frame packing configuration for the first RAS may be different than the frame packing configuration for the second RAS. The frame packing configuration for the first RAS and the frame packing configuration for the second RAS may be signaled in the video bitstream.

Abstract: Systems, methods, and instrumentalities are disclosed for performing horizontal geometry padding on a current sample based on receiving a wraparound enabled indication that indicates whether a horizontal wraparound motion compensation is enabled. If the horizontal wraparound motion compensation is enabled based on the wraparound enabled indication, a video coding device may determine a reference sample wraparound offset of a current sample in a picture. The reference sample wraparound offset may indicate a face width of the picture. The video coding device may determine a reference sample location for the current sample based on the reference sample wraparound offset, a picture width of the picture, and a current sample location. The video coding device may predict the current sample based on the reference sample location in a horizontal direction. Repetitive padding or clipping may be used in the vertical direction.

Abstract: Systems, methods, and instrumentalities are disclosed for discontinuous face boundary filtering for 360-degree video coding. A face discontinuity may be filtered (e.g., to reduce seam artifacts) in whole or in part, for example, using coded samples or padded samples on either side of the face discontinuity. Filtering may be applied, for example, as an in-loop filter or a post-processing step. 2D positional information related to two sides of the face discontinuity may be signaled in a video bitstream so that filtering may be applied independent of projection formats and/or frame packing techniques.

Abstract: Systems, methods, and instrumentalities may be provided for discounting reconstructed samples and/or coding information from spatial neighbors across face discontinuities. Whether a current block is located at a face discontinuity may be determined. The face discontinuity may be a face boundary between two or more adjoining blocks that are not spherical neighbors. The coding availability of a neighboring block of the current block may be determined, e.g., based on whether the neighboring block is on the same side of the face discontinuity as the current block. For example, the neighboring block may be determined to be available for decoding the current block if it is on the same side of the face discontinuity as the current block, and unavailable if it is not on the same side of the face discontinuity. The neighboring block may be a spatial neighboring block or a temporal neighboring block.

Abstract: Processing video data may include capturing the video data with multiple cameras and stitching the video data together to obtain a 360-degree video. A frame-packed picture may be provided based on the captured and stitched video data. A current sample location may be identified in the frame-packed picture. Whether a neighboring sample location is located outside of a content boundary of the frame-packed picture may be determined. When the neighboring sample location is located outside of the content boundary, a padding sample location may be derived based on at least one circular characteristic of the 360-degree video content and the projection geometry. The 360-degree video content may be processed based on the padding sample location.

Abstract: Systems, methods, and instrumentalities are disclosed for motion vector clipping when affine motion mode is enabled for a video block. A video coding device may determine that an affine mode for a video block is enabled. The video coding device may determine a plurality of control point affine motion vectors associated with the video block. The video coding device may store the plurality of clipped control point affine motion vectors for motion vector prediction of a neighboring control point affine motion vector. The video coding device may derive a sub-block motion vector associated with a sub-block of the video block, clip the derived sub-block motion vector, and store it for spatial motion vector prediction or temporal motion vector prediction. For example, the video coding device may clip the derived sub-block motion vector based on a motion field range that may be based on a bit depth value.

Abstract: A video coding device may be configured to periodically select the frame packing configuration (e.g., face layout and/or face rotations parameters) associated with a RAS, The device may receive a plurality of pictures, which may each comprise a plurality of faces. The pictures may be grouped Into a plurality of RASs. The device may select a frame packing configuration with the lowest cost for a first RAS. For example, the cost of a frame packing configuration may be determined based on the first picture of the first RAS. The device may select a frame packing configuration for a second RAS. The frame packing configuration for the first RAS may be different than the frame packing configuration for the second RAS. The frame packing configuration for the first RAS and the frame packing configuration for the second RAS may be signaled in the video bitstream.

Abstract: Systems, methods, and instrumentalities are disclosed for discontinuous face boundary filtering for 360-degree video coding. A face discontinuity may be filtered (e.g., to reduce seam artifacts) in whole or in part, for example, using coded samples or padded samples on either side of the face discontinuity. Filtering may be applied, for example, as an in-loop filter or a post-processing step. 2D positional information related to two sides of the face discontinuity may be signaled. In a video bitstream so that filtering may be applied independent of projection formats and/or frame packing techniques.

Abstract: Systems, methods, and instrumentalities may be provided for discounting reconstructed samples and/or coding information from spatial neighbors across face discontinuities. Whether a current block is located at a face discontinuity may be determined. The face discontinuity may be a face boundary between two or more adjoining blocks that are not spherical neighbors. The coding availability of a neighboring block of the current block may be determined, e.g., based on whether the neighboring block is on the same side of the face discontinuity as the current block. For example, the neighboring block may be determined to be available for decoding the current block if it is on the same side of the face discontinuity as the current block, and unavailable if it Is not on the same side of the face discontinuity. The neighboring block may be a spatial neighboring block or a temporal neighboring block.

Abstract: Processing video data may include capturing the video data with multiple cameras and stitching the video data together to obtain a 360-degree video. A frame-packed picture may be provided based on the captured and stitched video data. A current sample location may be identified in the frame-packed picture. Whether a neighboring sample location is located outside of a content boundary of the frame-packed picture may be determined. When the neighboring sample location is located outside of the content boundary, a padding sample location may be derived based on at least one circular characteristic of the 360-degree video content and the projection geometry. The 360-degree video content may be processed based on the padding sample location.