A method of managing the flow of data through a video decoder is described. The method includes receiving a stream of video data including compressed video frames organized in groups-of-pictures (GOP). A GOP typically includes one intra-frame coded image and a plurality of inter-frame coded images. Data included in received GOPs as uniquely identified GOP data blocks with uniquely identified compressed video frames are entered in a pre-decode cache module and they are selected, based on a current playback status, to be appended to a decode queue for GOP data blocks that will be delivered as input to a video decoder (106). Output data from the decoder (106) is delivered as decoded video frames to a post-decode cache module (303). Also described is a video decoder and a software program product.

Innovations in adaptive encoding for units of a video sequence can improve coding efficiency. For example, some of the innovations relate to encoding that includes adaptive switching of color spaces between units within a video sequence. Other innovations relate encoding that includes adaptive switching of color sampling rates between units within a video sequence. Still other innovations relate encoding that includes adaptive switching of bit depths between units within a video sequence.

Innovations in adaptive encoding for units of a video sequence can improve coding efficiency. For example, some of the innovations relate to encoding that includes adaptive switching of color spaces between units within a video sequence. Other innovations relate encoding that includes adaptive switching of color sampling rates between units within a video sequence. Still other innovations relate encoding that includes adaptive switching of bit depths between units within a video sequence.

In the present disclosure, a method of decoding a video signal and a device therefor are disclosed. Specifically, a method of decoding an image based on an inter prediction mode includes deriving a motion vector of an available spatial neighboring block around a current block; deriving a collocated block of the current block based on the motion vector of the spatial neighboring block; deriving a motion vector in a sub-block unit in the current block based on a motion vector of the collocated block; and generating a prediction block of the current block using the motion vector derived in the sub-block unit, wherein the collocated block may be specified by the motion vector of the spatial neighboring block in one pre-defined reference picture.

In the present disclosure, a method of decoding a video signal and a device therefor are disclosed. Specifically, a method of decoding an image based on an inter prediction mode includes deriving a motion vector of an available spatial neighboring block around a current block; deriving a collocated block of the current block based on the motion vector of the spatial neighboring block; deriving a motion vector in a sub-block unit in the current block based on a motion vector of the collocated block; and generating a prediction block of the current block using the motion vector derived in the sub-block unit, wherein the collocated block may be specified by the motion vector of the spatial neighboring block in one pre-defined reference picture.

The present invention includes obtaining block type identification information on a partition of the current macroblock when the current macroblock is intra-mixed, specifying a bock type of the current macroblock based on the block type identification information, obtaining an ultra prediction mode of the current macroblock according to the block type of the partition of the current macroblock, and predicting the current macroblock using the intra prediction mode and a pixel value of a neighboring block.

The present invention includes obtaining block type identification information on a partition of the current macroblock when the current macroblock is intra-mixed, specifying a bock type of the current macroblock based on the block type identification information, obtaining an ultra prediction mode of the current macroblock according to the block type of the partition of the current macroblock, and predicting the current macroblock using the intra prediction mode and a pixel value of a neighboring block.

A frame processor may generate a mask based on one or more static regions of a first set of frames of a plurality of previous frame and adjust the mask to at least one of determine alpha data or conceal distorted content associated with the one or more static regions of the first set of frames. The distorted content may be caused by extrapolation of a frame from a second set of frames of the plurality of previous frames. The frame processor may generate a composite frame based on application of at least one of the mask or the alpha data to a previous frame of the plurality of frames, and application of the previous frame based on the at least one of the mask or the alpha data to the frame extrapolated from the second set of frames of the plurality of previous frames.

Systems, methods, and computer-readable media for context-aware synthesis for video frame interpolation are provided. A convolutional neural network (ConvNet) may, given two input video or image frames, interpolate a frame temporarily in the middle of the two input frames by combining motion estimation and pixel synthesis into a single step and formulating pixel interpolation as a local convolution over patches in the input images. The ConvNet may estimate a convolution kernel based on a first receptive field patch of a first input image frame and a second receptive field patch of a second input image frame. The ConvNet may then convolve the convolutional kernel over a first pixel patch of the first input image frame and a second pixel patch of the second input image frame to obtain color data of an output pixel of the interpolation frame. Other embodiments may be described and/or claimed.

Memory required during decoding is reduced. A video image decoding device (1) is equipped with main direction deriving means (1453A) that references a prediction mode definition DEFPM(1), and from a prediction mode number, derives a main direction of a prediction direction corresponding to a prediction mode, and a gradient deriver (1453B) that references a gradient definition table DEFANG(1), and derives a gradient of the prediction direction.