Abstract: Techniques and systems are provided for image processing. For instance, a process can include: receiving an initial image rendered at a first time interval, the initial image having a larger field of view as compared to a field of view of a display; generating a mesh of vertices for the initial image, at least one vertex of the mesh corresponding to a portion of the initial image with the larger field of view; reprojecting the mesh of vertices based on a view angle change since the first time interval to obtain a reprojected mesh; generating estimated distortion information for the at least one vertex of the reprojected mesh corresponding to a portion of the initial image with the larger field of view; pre-distorting the reprojected mesh based on the estimated distortion information; and rasterizing the initial image based on the pre-distorted reprojected mesh to generate a reprojected image.

Abstract: This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for sparse composition. A processor obtains at least one frame including at least one component, where the at least one component includes (1) data of the at least one component and (2) metadata of the at least one component, and where the metadata includes enclosing boundary information of the at least one component. The processor predicts, based on the enclosing boundary information and pose information, a set of boundary coordinates of the at least one component. The processor adjusts, based on a display order, the predicted set of boundary coordinates of the at least one component. The processor determines whether the predicted set of boundary coordinates overlaps with at least one component boundary associated with a composition engine. The processor processes, based on the determination, the data.

Abstract: Techniques and systems are provided for image processing. For instance, a process can include: receiving an initial image rendered at a first time interval, the initial image having a larger field of view as compared to a field of view of a display; generating a mesh of vertices for the initial image, at least one vertex of the mesh corresponding to a portion of the initial image with the larger field of view; reprojecting the mesh of vertices based on a view angle change since the first time interval to obtain a reprojected mesh; generating estimated distortion information for the at least one vertex of the reprojected mesh corresponding to a portion of the initial image with the larger field of view; pre-distorting the reprojected mesh based on the estimated distortion information; and rasterizing the initial image based on the pre-distorted reprojected mesh to generate a reprojected image.

Abstract: Aspects presented herein relate to methods and devices for graphics processing including an apparatus, e.g., a GPU. The apparatus may receive a plurality of pixels associated with a first color space including a plurality of first color channels, at least one first color channel of the plurality of first color channels being a first compressed channel. The apparatus may also decompress the at least one first color channel of the plurality of first color channels, the at least one first color channel being decompressed from the first compressed channel to a first decompressed channel. Further, the apparatus may perform a color space conversion of the first color space associated with the plurality of pixels, such that the plurality of first color channels is converted to a plurality of second color channels, the plurality of second color channels being associated with a second color space for the plurality of pixels.

Abstract: Aspects presented herein relate to methods and devices for graphics processing including an apparatus, e.g., a GPU. The apparatus may receive a plurality of pixels associated with a first color space including a plurality of first color channels, at least one first color channel of the plurality of first color channels being a first compressed channel. The apparatus may also decompress the at least one first color channel of the plurality of first color channels, the at least one first color channel being decompressed from the first compressed channel to a first decompressed channel. Further, the apparatus may perform a color space conversion of the first color space associated with the plurality of pixels, such that the plurality of first color channels is converted to a plurality of second color channels, the plurality of second color channels being associated with a second color space for the plurality of pixels.

Abstract: The present disclosure relates to methods and apparatus for graphics processing. The apparatus can obtain at least one input image including a plurality of pixels. Additionally, the apparatus can determine shading information for each of the plurality of pixels in the at least one input image. The apparatus can also determine a shading map based on the determined shading information for each of the plurality of pixels in the at least one input image. In some aspects, the apparatus can generate at least one output image based on the at least one input image and the determined shading map. The apparatus can also enhance a quality of the at least one output image. In some aspects, the quality of the at least one output image can be enhanced based on machine learning. Further, the apparatus can generate the at least one input image including the plurality of pixels.

Abstract: An exemplary method for intelligent compression uses a foveated-compression approach. First, the location of a fixation point within an image frame is determined. Next, the image frame is sectored into two or more sectors such that one of the two or more sectors is designated as a fixation sector and the remaining sectors are designated as foveation sectors. A sector may be defined by one or more tiles within the image frame. The fixation sector includes the particular tile that contains the fixation point and is compressed according to a lossless compression algorithm. The foveation sectors are compressed according to lossy compression algorithms. As the locations of foveation sectors increase in angular distance from the location of the fixation sector, a compression factor may be increased.

Abstract: Scheduling image composition in a processor based on overlapping of an image composition process and image scan-out operation for displaying an image is disclosed. The processor is configured to periodically schedule a composition process to generate composition passes on the received eyebuffers to generate a display-corrected image for scan-out to a display device. To reduce the motion-to-photon latency, the processor is configured to delay scheduling of the composition process to be closer in time to the scan-out deadline such that there is an overlap in execution of the composition process at the scan-out deadline and image scan-out operation. The scheduling of the composition process can be delayed to only generate a desired number of display lines for the display-corrected image before the scan-out deadline such that lines of the display-corrected image can continue to be available faster than needed for scanning out by the image scan-out operation without scan-out delay.

Abstract: The present disclosure relates to methods and apparatus for graphics processing. The apparatus can obtain at least one input image including a plurality of pixels. Additionally, the apparatus can determine shading information for each of the plurality of pixels in the at least one input image. The apparatus can also determine a shading map based on the determined shading information for each of the plurality of pixels in the at least one input image. In some aspects, the apparatus can generate at least one output image based on the at least one input image and the determined shading map. The apparatus can also enhance a quality of the at least one output image. In some aspects, the quality of the at least one output image can be enhanced based on machine learning. Further, the apparatus can generate the at least one input image including the plurality of pixels.

Abstract: An exemplary method for intelligent compression uses a foveated-compression approach. First, the location of a fixation point within an image frame is determined. Next, the image frame is sectored into two or more sectors such that one of the two or more sectors is designated as a fixation sector and the remaining sectors are designated as foveation sectors. A sector may be defined by one or more tiles within the image frame. The fixation sector includes the particular tile that contains the fixation point and is compressed according to a lossless compression algorithm. The foveation sectors are compressed according to lossy compression algorithms. As the locations of foveation sectors increase in angular distance from the location of the fixation sector, a compression factor may be increased.

Abstract: An exemplary method for intelligent compression uses a foveated-compression approach. First, the location of a fixation point within an image frame is determined. Next, the image frame is sectored into two or more sectors such that one of the two or more sectors is designated as a fixation sector and the remaining sectors are designated as foveation sectors. A sector may be defined by one or more tiles within the image frame. The fixation sector includes the particular tile that contains the fixation point and is compressed according to a lossless compression algorithm. The foveation sectors are compressed according to lossy compression algorithms. As the locations of foveation sectors increase in angular distance from the location of the fixation sector, a compression factor may be increased.

Abstract: An exemplary method for intelligent compression uses a foveated-compression approach. First, the location of a fixation point within an image frame is determined. Next, the image frame is sectored into two or more sectors such that one of the two or more sectors is designated as a fixation sector and the remaining sectors are designated as foveation sectors. A sector may be defined by one or more tiles within the image frame. The fixation sector includes the particular tile that contains the fixation point and is compressed according to a lossless compression algorithm. The foveation sectors are compressed according to lossy compression algorithms. As the locations of foveation sectors increase in angular distance from the location of the fixation sector, a compression factor may be increased.

Abstract: Aspects of this disclosure relate to a device for generating image content that includes a memory and processing circuitry coupled to the memory. The processing circuitry is configured to determine a dithered fractional VRS value for a core block based on a dithering factor for the core block and a fractional VRS value for the core block and determine a dithered fractional shading rate based on the dithered fractional VRS value. The processing circuitry is further configured to render the image based on the dithered fractional shading rate.

Abstract: Methods and devices for managing data flows for concurrent multimedia applications executing on a device including a SoC, in response to determining that a temperature or power consumption exceeds a threshold are disclosed. A lowest priority data flow may be identified. A data flow path associated with the identified lowest priority data flow may be traced. A multimedia parameter of any hardware module along the data flow path may be reduced. When the temperature or power consumption no longer exceeds the threshold, a highest priority data flow among the multimedia applications that has had the multimedia parameter reduced may be identified. A data flow path for a data flow associated with the identified highest priority data flow may be traced. The multimedia parameter may be restored to an original value along the traced data flow path for the data flow associated with the identified highest priority data flow.

Abstract: Methods and devices for managing data flows for concurrent multimedia applications executing on a device including a SoC, in response to determining that a temperature or power consumption exceeds a threshold are disclosed. A lowest priority data flow may be identified. A data flow path associated with the identified lowest priority data flow may be traced. A multimedia parameter of any hardware module along the data flow path may be reduced. When the temperature or power consumption no longer exceeds the threshold, a highest priority data flow among the multimedia applications that has had the multimedia parameter reduced may be identified. A data flow path for a data flow associated with the identified highest priority data flow may be traced. The multimedia parameter may be restored to an original value along the traced data flow path for the data flow associated with the identified highest priority data flow.