Techniques related to graphics rendering including techniques for compression and/or decompression of graphics data by use of indexed subsets are described.

A method is described that includes loading an array of content into a two-dimensional shift register. The two-dimensional shift register is coupled to an execution lane array. The method includes repeatedly performing a first sequence including: shifting with the shift register first content residing along a particular row or column into another parallel row or column where second content resides and performing operations with a particular corresponding row or column of the execution lane array on the first and second content. The method also includes repeatedly performing a second sequence including: shifting with the shift register content from a set of first locations along a resultant row or column that is parallel with the rows or columns of the first sequence into a corresponding set of second locations along the resultant row or column. The resultant row or column has values determined from the operations of the first sequence.

Two-dimensional objects are displayed upon a user interface; user input selects an area and selects a machine learning model for execution. The results are displayed as an overlay over the objects in the user interface. User input selects a second model for execution; the result of this execution is displayed as a second overlay over the objects. A first overlay from a model is displayed over a set of objects in a user interface and a ground truth corresponding to the objects is displayed as a second overlay on the user interface. User input selects the ground truth overlay as a reference and causes a comparison of the first overlay with the ground truth overlay; the visual data from the comparison is displayed on the user interface. A comparison of M inference overlays with N reference overlays is performed and visual data from the comparison is displayed on the interface.

Two-dimensional objects are displayed upon a user interface; user input selects an area and selects a machine learning model for execution. The results are displayed as an overlay over the objects in the user interface. User input selects a second model for execution; the result of this execution is displayed as a second overlay over the objects. A first overlay from a model is displayed over a set of objects in a user interface and a ground truth corresponding to the objects is displayed as a second overlay on the user interface. User input selects the ground truth overlay as a reference and causes a comparison of the first overlay with the ground truth overlay; the visual data from the comparison is displayed on the user interface. A comparison of M inference overlays with N reference overlays is performed and visual data from the comparison is displayed on the interface.

Described herein are various technologies pertaining to presenting, and configuring, digital objects on a display device for application with a visual music presentation. An interactive screen can be presented on a touchscreen of a display device, wherein a visual musician can interact with one or more components and/or features comprising the screen to control presentation of the digital objects. A portion of the screen can be configured to initially present a continuous hue spectrum, which can subsequently be replaced with a discrete hue spectrum. Further, a spectrum comprising naturally visible hues can be modified such that a plurality of hues in the spectrum are positioned equally across the spectrum, and further, brightness of respective hues can be modified to enable visually appealing visual music presentation.

Described herein are various technologies pertaining to presenting, and configuring, digital objects on a display device for application with a visual music presentation. An interactive screen can be presented on a touchscreen of a display device, wherein a visual musician can interact with one or more components and/or features comprising the screen to control presentation of the digital objects. A portion of the screen can be configured to initially present a continuous hue spectrum, which can subsequently be replaced with a discrete hue spectrum. Further, a spectrum comprising naturally visible hues can be modified such that a plurality of hues in the spectrum are positioned equally across the spectrum, and further, brightness of respective hues can be modified to enable visually appealing visual music presentation.

A user device provides a user interface for video manipulation with face replacement. A method of implementations includes accessing a video comprising a plurality of frames that comprise one or more faces, providing a plurality of stickers comprising alternate face graphics for the one or more faces, receiving, via a user interface of a user device, user selection of one of the stickers and a selected face of the one or more faces, accessing a plurality of face frame sequences of the video, wherein each face frame sequence is a sequence of frames of the video comprising the selected face of the one or more faces, and replacing the selected face with the selected sticker in a first face frame sequence of the plurality of face frame sequences and in a second face frame sequence of the plurality of face frame sequences.

A user device provides a user interface for video manipulation with face replacement. A method of implementations includes accessing a video comprising a plurality of frames that comprise one or more faces, providing a plurality of stickers comprising alternate face graphics for the one or more faces, receiving, via a user interface of a user device, user selection of one of the stickers and a selected face of the one or more faces, accessing a plurality of face frame sequences of the video, wherein each face frame sequence is a sequence of frames of the video comprising the selected face of the one or more faces, and replacing the selected face with the selected sticker in a first face frame sequence of the plurality of face frame sequences and in a second face frame sequence of the plurality of face frame sequences.

A graphics processing unit (GPU) processes graphics data using a rendering space which is sub-divided into a plurality of tiles. The GPU comprises cost indication logic configured to obtain a cost indication for each of a plurality of sets of one or more tiles of the rendering space. The cost indication for a set of tile(s) is suggestive of a cost of processing the set of one or more tiles. The GPU controls a rendering complexity with which primitives are rendered in tiles based on the cost indication for those tiles. This allows tiles to be rendered in a manner that is suitable based on the complexity of the graphics data within the tiles. In turn, this allows the rendering to satisfy constraints such as timing constraints even when the complexity of different tiles may vary significantly within an image.

A graphics processing unit (GPU) processes graphics data using a rendering space which is sub-divided into a plurality of tiles. The GPU comprises cost indication logic configured to obtain a cost indication for each of a plurality of sets of one or more tiles of the rendering space. The cost indication for a set of tile(s) is suggestive of a cost of processing the set of one or more tiles. The GPU controls a rendering complexity with which primitives are rendered in tiles based on the cost indication for those tiles. This allows tiles to be rendered in a manner that is suitable based on the complexity of the graphics data within the tiles. In turn, this allows the rendering to satisfy constraints such as timing constraints even when the complexity of different tiles may vary significantly within an image.