Neural network-based image processing with artifact compensation

    公开(公告)号:US11893711B2

    公开(公告)日:2024-02-06

    申请号:US17841387

    申请日:2022-06-15

    Applicant: Apple Inc.

    Abstract: Methods and systems include neural network-based image processing and blending circuitry to blend an output of the neural network to compensate for potential artifacts from the neural network-based image processing. The neural network(s) apply image processing to image data using one or more neural networks as processed data. Enhance circuitry enhances the image data in a scaling circuitry to generate enhanced data. Blending circuitry receives the processed image data and the enhanced data along with an image plane of the processed data. The blending circuitry also determines whether the image processing using the one or more neural networks has applied a change to the image data greater than a threshold amount. The blending circuitry then, based at least in part in response to the change being greater than the threshold amount and/or edge information of the image data, blends the processed data with the enhanced data.

    Dynamic foveated pipeline
    2.
    发明授权

    公开(公告)号:US11836885B2

    公开(公告)日:2023-12-05

    申请号:US17053181

    申请日:2019-05-06

    Applicant: Apple Inc.

    CPC classification number: G06T3/0093 G06T3/40 G06T9/001

    Abstract: In one implementation, a method includes receiving a warped image representing simulated reality (SR) content (e.g., to be displayed in a display space), the warped image having a plurality of pixels at respective locations uniformly spaced in a grid pattern in a warped space, wherein the plurality of pixels are respectively associated with a plurality of respective pixel values and a plurality of respective scaling factors indicating a plurality of respective resolutions at a plurality of respective locations of the SR content (e.g., in the display space). The method includes processing the warped image in the warped space based on the plurality of respective scaling factors to generate a processed warped image and transmitting the processed warped image.

    PRIORITY-BASED VIDEO ENCODING AND TRANSMISSION

    公开(公告)号:US20230092305A1

    公开(公告)日:2023-03-23

    申请号:US18052807

    申请日:2022-11-04

    Applicant: Apple Inc.

    Abstract: A video encoding system in which pixel data is decomposed into frequency bands prior to encoding. The frequency bands are organized into blocks that are provided to a block-based encoder that encodes the blocks and passes the encoded blocks to a wireless interface that packetizes the blocks for transmittal over a wireless connection. The encoder may categorize the encoded frequency bands into multiple priority levels, and may tag each frequency block with metadata indicating the frequency band represented in the block, the priority of the frequency band, and timing information. The wireless interface may then transmit or drop packets according to the priority levels of the encoded frequency blocks in the packets and/or according to the timing information of the frequency blocks in the packets.

    Rate control for low latency video encoding and transmission

    公开(公告)号:US11451788B2

    公开(公告)日:2022-09-20

    申请号:US17252701

    申请日:2019-06-27

    Applicant: Apple Inc.

    Abstract: A video encoding system in which pixel data is decomposed into frequency bands prior to encoding. The frequency bands for a slice of a frame may be buffered so that complexity statistics may be calculated across the frequency bands prior to encoding. The statistics may then be used by a rate control component in determining quantization parameters for the frequency bands for modulating the rate in the encoder for the current slice. The quantization parameters for the frequency bands may be calculated jointly to optimize the quality of the displayed frames after decoder reconstruction and wavelet synthesis on a receiving device. Information about one or more previously processed frames may be used in combination with the statistics for a current slice in determining the quantization parameters for the current slice.

    PRIORITY-BASED VIDEO ENCODING AND TRANSMISSION

    公开(公告)号:US20210274200A1

    公开(公告)日:2021-09-02

    申请号:US17252697

    申请日:2019-06-27

    Applicant: Apple Inc.

    Abstract: A video encoding system in which pixel data is decomposed into frequency bands prior to encoding. The frequency bands are organized into blocks that are provided to a block-based encoder that encodes the blocks and passes the encoded blocks to a wireless interface that packetizes the blocks for transmittal over a wireless connection. The encoder may categorize the encoded frequency bands into multiple priority levels, and may tag each frequency block with metadata indicating the frequency band represented in the block, the priority of the frequency band, and timing information. The wireless interface may then transmit or drop packets according to the priority levels of the encoded frequency blocks in the packets and/or according to the timing information of the frequency blocks in the packets.

    CHROMINANCE AND LUMINANCE ENHANCING SYSTEMS AND METHODS

    公开(公告)号:US20200043138A1

    公开(公告)日:2020-02-06

    申请号:US16053342

    申请日:2018-08-02

    Applicant: Apple Inc.

    Abstract: An electronic device may include enhancement circuitry to enhance high resolution image data to improve perceived quality of an image corresponding to the high resolution image data. The enhancement circuitry may include tone detection circuitry to determine one or more tones within the image and apply changes to the high resolution image data based on the one or more tones. The enhancement circuitry may also include example-based improvement circuitry to compare the high resolution image data to low resolution image data and apply changes to the high resolution image data based on differences between sections of the high resolution image data and sections of the low resolution image data. The enhancement circuitry may also include channel processing circuitry to apply the first and second changes to one or more channels of the high resolution image data.

    Error concealment for a head-mountable device

    公开(公告)号:US10521881B1

    公开(公告)日:2019-12-31

    申请号:US16015788

    申请日:2018-06-22

    Applicant: Apple Inc.

    Abstract: In various implementations, a method includes obtaining a first frame that is characterized by a first resolution associated with a first memory allocation. In some implementations, the method includes down-converting the first frame from the first resolution to a second resolution that is lower than the first resolution initially defining the first frame in order to produce a reference frame. In some implementations, the second resolution is associated with a second memory allocation that is less than a target memory allocation derived from the first memory allocation. In some implementations, the method includes storing the reference frame in a non-transitory memory. In some implementations, the method includes obtaining a second frame that is characterized by the first resolution. In some implementations, the method includes performing an error correction operation on the second frame based on the reference frame stored in the non-transitory memory.

    Data storage and access in block processing pipelines
    10.
    发明授权
    Data storage and access in block processing pipelines 有权
    块处理管道中的数据存储和访问

    公开(公告)号:US09571846B2

    公开(公告)日:2017-02-14

    申请号:US14039764

    申请日:2013-09-27

    Applicant: Apple Inc.

    CPC classification number: H04N19/423 H04N19/53

    Abstract: Block processing pipeline methods and apparatus in which reference data are stored to a memory according to tile formats to reduce memory accesses when fetching the data from the memory. When the pipeline stores reference data from a current frame being processed to memory as a reference frame, the reference samples are stored in macroblock sequential order. Each macroblock sample set is stored as a tile. Reference data may be stored in tile formats for luma and chroma. Chroma reference data may be stored in tile formats for chroma 4:2:0, 4:2:2, and/or 4:4:4 formats. A stage of the pipeline may write luma and chroma reference data for macroblocks to memory according to one or more of the macroblock tile formats in a modified knight's order. The stage may delay writing the reference data from the macroblocks until the macroblocks have been fully processed by the pipeline.

    Abstract translation: 块处理管道方法和装置,其中参考数据根据瓦片格式存储到存储器中,以在从存储器取出数据时减少存储器访问。 当流水线将正在处理的当前帧的参考数据存储为参考帧时,参考样本以宏块顺序存储。 每个宏块样本集被存储为一个图块。 参考数据可以以瓦片和色度的瓦片格式存储。 色度参考数据可以以瓦4:2:0,4:2:2和/或4:4:4格式的瓦片格式存储。 流水线的一个阶段可以根据改进的骑士顺序中的一个或多个宏块瓦片格式将宏块的亮度和色度参考数据写入存储器。 该阶段可以延迟从宏块写入参考数据,直到宏块已被管道完全处理。

Patent Agency Ranking