Mediatek Corporation

Chia-Yun Cheng

Yung-Chang Chang

Sheng-Jen Wang

Han-Liang Chou

Min-Hao Chiu

Ming-Long Wu

Chi-Cheng Ju

Chih-Ming Wang

Tzu-Der Chuang

Ching-Yeh Chen

Yu-Wen Huang

Yu-Chen Sun

Chun-Chia Chen

Chi-Hung Chen

Meng-Jye Hu

Chao-I Wu

Tung-Hsing Wu

Kai-Chun Lin

Ping Chao

Li-Heng Chen

Ting-An Lin

Huei-Min Lin

Yi-Hsin Huang

Chung-Hua Tsai

Jun Cui

Shun-Hsiang Chuang

Chih-Wen Yang

Cheng-Han Li

Hong-Cheng Lin

Hsuan-Wen Peng

Yun-Feng Tseng

Ming-Hsien Lai

A context-based adaptive binary arithmetic coding (CABAC) decoder includes a bin decode circuit and a context update circuit. The bin decode circuit supports decoding of multiple bins in one cycle. The multiple bins include a first bin and a second bin. The bin decode circuit generates a bin value of the first bin according to a first set of multiple contexts, a first range and a first offset, and generates one bin value of the second bin according to a second set of multiple contexts, a second range and a second offset. The context update circuit updates the first set of multiple contexts in response to the bin value of the first bin, to generate a first set of multiple updated contexts, and updates the second set of multiple contexts in response to said one bin value of the second bin, to generate a second set of multiple updated contexts.

Context-based adaptive binary arithmetic coding decoder capable of decoding multiple bins in one cycle and associated decoding method

A video decoding method includes: before residual decoding of a coding unit is completed, referring to available information to determine whether to decode information that an inverse transform (IT) circuit needs for applying inverse transform to transform blocks of the coding unit, and generating a determination result; and controlling coefficient transmission of the coding unit to the IT circuit according to the determination result.

Method and apparatus for contorlling coefficient transmission by early determining whether to decode information that inverse transform needs

A motion vector (MV) projection method includes generating motion field motion vectors (MFMVs) for a first portion of a current frame by applying MV projection to MVs of a portion of each of reference frames and storing the MFMVs of the first portion of the current frame into an MFMV buffer, and generating MFMVs for a second portion of the current frame by applying MV projection to MVs of a portion of each of the reference frames and storing the MFMVs of the second portion of the current frame into the MFMV buffer. The second portion does not overlap the first portion. Before generating the MFMVs for the second portion of the current frame is done, at least one of the MFMVs of the first portion is read from the MFMV buffer and involved in motion vector determination of at least one coding block included in the first portion.

Method and apparatus for generating motion field motion vectors for blocks of current frame in on-the-fly manner

A video processing system includes a storage device, a receiving circuit, an audio/video demultiplexing circuit, a video decoder, and a display engine. The storage device includes a data buffer, a bitstream buffer, and a display buffer. An output of the receiving circuit is written into the data buffer. An input of the audio/video demultiplexing circuit is read from the data buffer, and an output of the audio/video demultiplexing circuit is written into the bitstream buffer. An input of the video decoder is read from the bitstream buffer, and an output of the video decoder is written into the display buffer. An input of the display engine is read from the display buffer. Each of the data buffer, the bitstream buffer, and the display buffer is a ring buffer.

Video processing system using ring buffer and racing-mode ring buffer access control scheme

A post processing apparatus includes a super-resolution (SR) filtering circuit and a loop restoration (LR) filtering circuit. The SR filtering circuit applies SR filtering to a processing result of a preceding circuit. The LR filtering circuit applies LR filtering to a processing result of the SR filtering circuit. Before the SR filtering circuit finishes SR filtering of all pixels of a frame that are generated by the preceding circuit, the LR filtering circuit starts LR filtering of pixels that are derived from applying SR filtering to pixels included in the frame.

Post processing apparatus with super-resolution filter and loop restoration filter in block-level pipeline and associated post processing method

An entropy decoding apparatus includes an entropy decoding circuit, a pre-fetch circuit, and a context pre-load buffer. The pre-fetch circuit pre-fetches at least one candidate context for entropy decoding of a part of an encoded bitstream of a frame before the entropy decoding circuit starts entropy decoding of the part of the encoded bitstream of the frame. The context pre-load buffer buffers the at least one candidate context. When a target context actually needed by entropy decoding of the part of the encoded bitstream of the frame is not available in the context pre-load buffer, the context pre-load buffer instructs the pre-fetch circuit to re-fetch the target context, and the entropy decoding circuit stalls entropy decoding of the part of the encoded bitstream of the frame.

Entropy decoding apparatus with context pre-fetch and miss handling and associated entropy decoding method

A video encoder has a processing circuit and a universal binary entropy (UBE) syntax encoder. The processing circuit processes pixel data of a video frame to generate encoding-related data, wherein the encoding-related data comprise at least quantized transform coefficients. The UBE syntax encoder processes a plurality of syntax elements to generate UBE syntax data. The encoding-related data are represented by the syntax elements. The processing circuit operates according to a video coding standard. The video coding standard supports arithmetic encoding. The UBE syntax data contain no arithmetic-encoded syntax data.

Video processing system using low-cost video encoding/decoding architecture

A method and apparatus of sharing an on-chip buffer or cache memory for a video coding system using coding modes including Inter prediction mode or Intra Block Copy (IntraBC) mode are disclosed. At least partial pre-deblocking reconstructed video data of a current picture is stored in an on-chip buffer or cache memory. If the current block is coded using IntraBC mode, the pre-deblocking reconstructed video data of the current picture stored in the on-chip buffer or cache memory are used to derive IntraBC prediction for the current block. In some embodiments, if the current block is coded using Inter prediction mode, Inter reference video data from the previous picture stored in the on-chip buffer or cache memory are used to derive Inter prediction for the current block. In another embodiment, the motion compensation/motion estimation unit is shared by the two modes.

Method and apparatus for resource sharing between intra block copy mode and inter prediction mode in video coding systems

Methods of palette coding to reduce the required coding process are disclosed. According to one method, smaller blocks are derived from a large block. The histogram of the large block is derived based on the histograms of smaller blocks in the large block. According to another method, one or more palette tables are derived based on multiple blocks. One palette table is used for each of the multiple blocks. According to yet another method, index map transpose is performed in the parsing stage according to the transpose flag of the index map. Accordingly, a buffer to store the transpose flags can be saved. According to still yet another method, the palette predictor update is performed using an index mapping table to avoid the need for shuffling the contents of the palette predictor stored in a palette buffer.

Methods for palette coding of image and video data

A video processing apparatus includes an external storage device, a hardware entropy engine, and a software execution engine. The hardware entropy engine performs entropy processing of a current picture, and further outputs count information to the external storage device during the entropy processing of the current picture. When loaded and executed by the software execution engine, a software program instructs the software execution engine to convert the count information into count table contents, and generate a count table in the external storage device according to at least the count table contents. The count table is referenced to apply a backward adaptation to a probability table that is selectively used by the hardware entropy engine to perform entropy processing of a next picture.

Video processing apparatus for generating count table in external storage device of hardware entropy engine and associated video processing method

In order to overcome the issue caused by a decoded block vector (BV) pointing to a reference block overlapping with an unavailable area, various methods are disclosed. According to one method, if the reference block overlaps with an unavailable area, the reference pixels in the unavailable area are generated for IntraBC prediction of the current block by padding from neighboring available pixels. The padding can be done in the horizontal direction and then the vertical direction. The padding may also done in the vertical direction first and then horizontal direction. In another method, if the reference block overlaps with an unavailable area, the reference pixels in the unavailable area are generated for IntraBC prediction of the current block by using previous decoded pixels in the unavailable area. A pre-defined value may also be used for the unavailable area.

Method and apparatus of error handling for video coding using intra block copy mode

A method and apparatus for video encoding or decoding used by an AVS2 (Second Generation of Audio Video Coding Standard) video encoder or decoder respectively are disclosed. According to this method, first motion vectors associated with spatial neighboring blocks of a current block are determined. For each spatial neighboring block, a value of 1 is assigned to a first BlockDistance associated with the spatial neighboring block if a corresponding first reference picture is a G picture or GB picture. Motion vector predictor candidates are derived from the first motion vectors by scaling each first motion vector according to a corresponding first BlockDistance and a current BlockDistance. A final motion vector predictor is determined among the motion vector predictor candidates. The current motion vector is encoded or decoded using the final motion vector predictor

Method and apparatus of motion vector prediction

An apparatus is capable of achieving high-throughput entropy decoding, and includes an arithmetic decoding processing circuitry and a variable-length decoder (VLD). The arithmetic decoding processing circuitry receives a video bitstream through a bitstream input, applies arithmetic decoding to at least a portion of the video bitstream to derive one or more arithmetic-decoded binary strings containing no arithmetic encoded binary string, and stores the arithmetic-decoded binary strings in the storage device. The variable-length decoder is coupled to the arithmetic decoding processing circuitry, the storage device and a VLD output. The variable-length decoder receives at least a portion of arithmetic-decoded bitstream when arithmetic-decoded bitstreams stored in the storage device are complete for a selected image unit, decodes at least a portion of arithmetic-decoded bitstream into one or more decoded syntax elements, and provides the decoded syntax elements through the VLD output.

Method and apparatus for entropy decoding with arithmetic decoding decoupled from variable-length decoding

A residual processing circuit has a single-path pipeline and a single-path controller. The single-path pipeline has an inverse scan (IS) circuit, an inverse quantization (IQ) circuit and an inverse transform (IT) circuit arranged to process a current non-zero residual data block in a pipeline manner. The current non-zero residual data block is at least a portion of a transform unit. The single-path controller controls pipelined processing of the current non-zero residual data block at the single-path pipeline. The single-path controller instructs the IS circuit to start IS processing of a next non-zero residual data block before the IT circuit finishes a first half of IT processing of the current non-zero residual data block.

Residual processing circuit using single-path pipeline or multi-path pipeline and associated residual processing method

A video transmitting system includes a source buffer, a video encoder, a bitstream buffer, and a transmitting circuit. The source buffer receives pixel data of pixels of a video frame. The video encoder retrieve pixel data of a portion of the pixels of the video frame from the source buffer, and starts encoding the pixel data of the portion of the pixels before pixel data of a last pixel of the video frame is received by the source buffer. The bitstream buffer receives a network abstraction layer (NAL) stream from the video encoder, wherein the NAL stream is generated by encoding the pixel data of the portion of the pixels. The transmitting circuit retrieves the NAL stream from the bitstream buffer, and starts outputting the NAL stream before the pixel data of the last pixel of the video frame is encoded by the video encoder.

Growing community of inventors

Hsinchu County, Taiwan

Chia-Yun Cheng