Abstract: An image decoding method includes: obtaining, from a bitstream, a first temporal motion vector prediction flag, which is a temporal motion vector prediction flag indicating whether or not temporal motion vector prediction is to be used, indicating that temporal motion vector prediction is not to be used on a first picture; decoding the first picture without using the temporal motion vector prediction; and decoding a second picture which follows the first picture in decoding order, with referring to a motion vector of a picture preceding the first picture in decoding order being prohibited.

Abstract: A method of encoding a video into a coded video bitstream with temporal motion vector prediction comprises: determining a value of a flag for indicating whether temporal motion vector prediction is used or not used for the inter-picture prediction of a sub-picture unit of a picture; and writing the flag having the value into a header of the sub-picture unit or a header of the picture; wherein if the flag indicates that temporal motion vector prediction is used, the method further comprises: creating a first list of motion vector predictors comprising a plurality of motion vector predictors including at least one temporal motion vector predictor derived from at least one motion vector from a collocated reference picture; selecting a motion vector predictor out of the first list; and writing a first parameter into the coded video bitstream for indicating the selected motion vector predictor out of the first list.

Abstract: An image generation apparatus includes: a pixel-shifted image generation unit which generates a first pixel-shifted image resulting from a process of shifting, based on an input image and a depth map, a pixel in the input image by a shift amount corresponding to the new viewpoint, and a second pixel-shifted image resulting from a process of shifting, by the same shift amount as for the first pixel-shifted image, a pixel in a background edge image included in the input image and containing a pixel located in a background region around an edge of a foreground object; an image fusion unit which fuses the second pixel-shifted image and the first pixel-shifted image to include a background region in the second pixel-shifted image into a hole; and a hole filling unit which fills the hole with pixel information based on the fused pixel-shifted image.

Abstract: A method of encoding a video into a coded video bitstream with temporal motion vector prediction comprises: determining a value of a flag for indicating whether temporal motion vector prediction is used or not used for the inter-picture prediction of a sub-picture unit of a picture; and writing the flag having the value into a header of the sub-picture unit or a header of the picture; wherein if the flag indicates that temporal motion vector prediction is used, the method further comprises: creating a first list of motion vector predictors comprising a plurality of motion vector predictors including at least one temporal motion vector predictor derived from at least one motion vector from a collocated reference picture; selecting a motion vector predictor out of the first list; and writing a first parameter into the coded video bitstream for indicating the selected motion vector predictor out of the first list.

Abstract: An image decoding method includes: obtaining, from a bitstream, a first temporal motion vector prediction flag, which is a temporal motion vector prediction flag indicating whether or not temporal motion vector prediction is to be used, indicating that temporal motion vector prediction is not to be used on a first picture; decoding the first picture without using the temporal motion vector prediction; and decoding a second picture which follows the first picture in decoding order, with referring to a motion vector of a picture preceding the first picture in decoding order being prohibited.

Abstract: An image coding method includes: selecting a first picture from plural pictures; setting a first temporal motion vector prediction flag which is associated with the first picture and is a temporal motion vector prediction flag indicating whether or not temporal motion vector prediction is to be used, to indicate that the temporal motion vector prediction is not to be used, and coding the first temporal motion vector prediction flag; coding the first picture without using the temporal motion vector prediction; and coding a second picture which follows the first picture in coding order, with referring to a motion vector of a picture preceding the first picture in coding order being prohibited.

Abstract: The present invention introduces new methods and apparatuses for decoded picture buffer (DPB) management using reference picture set (RPS) where consecutive reference picture sets are conFIG.d such that reference pictures is set/marked as non-reference at appropriate instances and/or according to predetermined priorities. Using the present invention, the DPB size is kept at a minimum while supporting both optimal reference picture configuration and correct output reordering. Benefits of the present invention are in the form of improved coding efficiency and/or reduced memory storage for DPB.

Abstract: An image generation apparatus includes: a pixel-shifted image generation unit which generates a first pixel-shifted image resulting from a process of shifting, based on an input image and a depth map, a pixel in the input image by a shift amount corresponding to the new viewpoint, and a second pixel-shifted image resulting from a process of shifting, by the same shift amount as for the first pixel-shifted image, a pixel in a background edge image included in the input image and containing a pixel located in a background region around an edge of a foreground object; an image fusion unit which fuses the second pixel-shifted image and the first pixel-shifted image to include a background region in the second pixel-shifted image into a hole; and a hole filling unit which fills the hole with pixel information based on the fused pixel-shifted image.