摘要:
An encoding/decoding apparatus and method for parallel correction of in-loop pixels based on complexity using a video parameter may include a complexity measuring unit to measure a complexity of an in-loop pixel correction process, using video codec parameter information, in a video codec, and a core allocating unit to evenly distribute jobs associated with the in-loop pixel correction process, using the measured complexity.
摘要:
An image data decoding apparatus and method are based on an availability of reference data. The image data decoding apparatus may include a core to process decoding of image data, and an availability determining device to receive, from the core, availability verification request information with respect to a reference area of a first frame included in the image data, to determine an availability with respect to the reference area based on the received availability verification request information, and to transmit, to the core, the determined availability. When the reference area is available, the core may process decoding of a second frame based on the reference area.
摘要:
A memory access address translating apparatus and method may each classify pixels included in an input image into a plurality of tiles, and may generate a new memory for each of the successive tiles to enable the successive tiles, among a plurality of tiles, to be stored in different banks.
摘要:
Provided is an apparatus and method of dynamically distributing load occurring in multiple cores that may determine a corresponding core to perform functions constituting an application program, thereby enhancing the entire processing rate.
摘要:
An apparatus and method provide parallel encoding and decoding of image data based on correlation of macroblocks. To encode and decode image data having a high resolution, an encoding order may be determined based on a correlation between blocks of the image data, and a decoding order may be determined based on the determined encoding order, thereby efficiently processing the blocks in parallel.
摘要:
An encoding/decoding apparatus and method for parallel correction of in-loop pixels based on complexity using a video parameter may include a complexity measuring unit to measure a complexity of an in-loop pixel correction process, using video codec parameter information, in a video codec, and a core allocating unit to evenly distribute jobs associated with the in-loop pixel correction process, using the measured complexity.
摘要:
An image data decoding apparatus and method are based on an availability of reference data. The image data decoding apparatus may include a core to process decoding of image data, and an availability determining device to receive, from the core, availability verification request information with respect to a reference area of a first frame included in the image data, to determine an availability with respect to the reference area based on the received availability verification request information, and to transmit, to the core, the determined availability. When the reference area is available, the core may process decoding of a second frame based on the reference area.
摘要:
A method and apparatus for restoring an image by copying a memory may include determining whether to perform an interpolation operation based on block information, and restoring a current image using a reference image depending on whether to perform the interpolation operation.
摘要:
A method and apparatus for restoring an image by copying a memory may include determining whether to perform an interpolation operation based on block information, and restoring a current image using a reference image depending on whether to perform the interpolation operation.
摘要:
An apparatus and method sequentially parses bitstreams based on a removal of an Emulation Prevention Byte (EPB). The apparatus and method may detect an EPB pattern from among sequentially input bitstreams, may store the bitstreams, may store a processed bitstream where the EPB pattern is removed, among the bitstreams, and may select an output of a register buffer based on an input of a buffer selection flag.