摘要:
An image processor generates an output image of a resolution higher than a resolution of an input image, using the input image. The image processor includes: an obtaining unit configured to obtain an edge strength of one of the input image and an image corresponding to the input image; a calculating unit configured to calculate, based on the edge strength, J that is a count of data items to be used for generating a synthesized image to be used in generating the output image, where J is an integer equal to or larger than 2; and a generating unit configured to generate the synthesized image by synthesizing J data items, and generate the output image using the synthesized image.
摘要:
A super-resolution processor according to the present invention includes: an N enlargement unit that generates an N-enlarged image by enlarging the input image by a factor N; an M enlargement unit that generates an M-enlarged image by enlarging the input image by a factor M; a high-pass filter unit that extracts a high-frequency component of the M-enlarged image, as an M-enlarged high-frequency image; a patch extraction unit that extracts an estimated patch of a predetermined size from the M-enlarged high-frequency image, the estimated patch being a part of the M-enlarged high-frequency image; and an addition unit that adds the estimated patch to a processing target block of the predetermined size in the N-enlarged image, to generate the output image, where M is smaller than N.
摘要:
An image processing method capable of appropriately increasing a resolution of an input image in which an edge direction that is a direction along an edge included in the input image is identified; a shape of an application region that is a region including at least a part of the edge is determined according to the identified edge direction; an image similar to an image within the application region having the determined shape is searched for; and an output image is generated by performing a resolution conversion process on the input image using the similar image so that the input image includes high-frequency components.
摘要:
In the image processing method capable of appropriately increasing a resolution of an input image: an edge direction that is a direction along an edge included in the input image is identified; a shape of an application region that is a region including at least a part of the edge is determined according to the identified edge direction; an image similar to an image within the application region having the determined shape is searched for; and an output image is generated by performing a resolution conversion process on the input image using the similar image so that the input image includes high-frequency components.
摘要:
An image processor generates an output image of a resolution higher than a resolution of an input image, using the input image. The image processor includes: an obtaining unit configured to obtain an edge strength of one of the input image and an image corresponding to the input image; a calculating unit configured to calculate, based on the edge strength, J that is a count of data items to be used for generating a synthesized image to be used in generating the output image, where J is an integer equal to or larger than 2; and a generating unit configured to generate the synthesized image by synthesizing J data items, and generate the output image using the synthesized image.
摘要:
A super-resolution processor in one aspect of the present invention first estimates a motion between an input image and a delayed input image which is obtained by delaying the input image by some frames, and determines a motion vector in super-resolution processing of adding a high frequency component using a learning database. Subsequently, the super-resolution processor updates an evaluation value evaluated when a patch is extracted in a target block of the input image, so that a learned high frequency patch is likely to be selected, the learned high frequency patch being the same as the learned high frequency patch used for super-resolution processing performed at the position motion-compensated by the motion vector in the frame at the same time as the time of the delayed input image.
摘要:
A super-resolution processor includes an N enlargement unit that generates an N-enlarged image by enlarging the input image by a factor N; an M enlargement unit that generates an M-enlarged image by enlarging the input image by a factor M; and a high-pass filter unit that extracts a high-frequency component of the M-enlarged image, as an M-enlarged high-frequency image. Additionally, a patch extraction unit extracts an estimated patch of a predetermined size from the M-enlarged high-frequency image, the estimated patch being a part of the M-enlarged high-frequency image; and an addition unit adds the estimated patch to a processing target block of the predetermined size in the N-enlarged image, to generate the output image, where M is smaller than N.
摘要:
The image decoding method includes: determining a context for use in a current block to be processed, from among a plurality of contexts; and performing arithmetic decoding on a bit sequence corresponding to the current block, using the determined context, wherein in the determining: the context is determined under a condition that control parameters of neighboring blocks of the current block are used, when the signal type is a first type, the neighboring blocks being a left block and an upper block of the current block; and the context is determined under a condition that the control parameter of the upper block is not used, when the signal type is a second type, and the second type is “no_residual_data_flag”.
摘要:
Methods and apparatuses for performing inter-color-plane prediction with adaptability to various existing video content representations are provided. A plurality of predetermined rescaling schemes based on a color plane format is selected. A first block of original samples of a first color plane is encoded into a compressed bitstream. A block of reconstructed samples of the first color plane is reconstructed. An inter-color-plane prediction process is performed to produce samples of a second color plane. Said block of prediction samples of the second color plane is subtracted from a second block of original samples of the second color plane to produce a block of residual samples of the second color plane where the positions of the first block and the second block of original samples are aligned. Finally, the block of residual samples of the second color plane is encoded.
摘要:
The image decoding method includes: determining a context for use in a current block to be processed, from among a plurality of contexts; and performing arithmetic decoding on a bit sequence corresponding to the current block, using the determined context, wherein in the determining: the context is determined under a condition that control parameters of neighboring blocks of the current block are used, when the signal type is a first type, the neighboring blocks being a left block and an upper block of the current block; and the context is determined under a condition that the control parameter of the upper block is not used, when the signal type is a second type.