Abstract: A local object classifier using a set of object definitions to perform object classification in image frames. The local object classifier is arranged to detect an object in an image frame and determine whether to transmit image data for the detected object to a remote object classifier. In response to said determining, the local object classifier is arranged to transmit image data, derived from the image data representative of the image frame, to the remote object classifier. The local object classifier is also arranged to receive object data, representative of the detected object, from the remote object classifier.

Abstract: A computer implemented method for performing convolutions between subsets of an input data array and a kernel resulting in subsets of an output data array. The method may include receiving an input data array and using positional data indicating the position of elements of the input data array to determine subsets of the input data array which contains at least one non-zero value data element; performing convolutions between the subsets of the input data array containing at least one non-zero value data element and a kernel to produce output data array subsets; and combining the output data subsets with the positional data to generate output data indicative of a completed output data array.

Abstract: A system for estimating a current camera pose corresponding to a current point in time using a previous camera pose corresponding to a previous point in time, of a camera configured to generate a sequence of image frames. The system performs operations, including: generating, using one or more neural networks, a neural network pose prediction for the current image frame; and adjusting a previous camera pose using inertial measurement unit data representing a motion of the camera between the previous point in time and the current point in time, to provide an inertial measurement unit pose prediction for the current point in time. The inertial measurement unit pose prediction, and the neural network pose prediction are combined in order to estimate the current camera pose.

Abstract: A graphics processing system and method of operating a graphics processing system that generates “spacewarped” frames for display is disclosed. Motion vectors are used to determine the motion of objects appearing in rendered application frames. The so-determined motion is then used to generate “spacewarped” versions of the rendered application frames.

Abstract: A data processing system operable to process a neural network, and comprising a plurality of processors. The data processing system is operable to determine whether to perform neural network processing using a single processor or using plural processors. When it is determined that plural processors should be used, a distribution of the neural network processing among two or more of the processors is determined and the two or more processors are each assigned a portion of the neural network processing to perform. A neural network processing output is provided as a result of the processors performing their assigned portions of the neural network processing.

Abstract: When rendering a new frame using a hybrid ray tracing process, a graphics processor transforms vertex position data for models representing objects in the new frame into camera space for use in a rasterisation process of the hybrid ray tracing process irrespective of whether the object has moved between frames or whether the geometry of the model representing object has changed, but only transforms vertex position data for a model for an object into world space for use in a ray tracing process of the hybrid ray tracing process when the object has moved between frames or where the geometry of the model representing the object has changed.

Abstract: When a programmable execution unit of a graphics processor is executing a graphics processing program to render a frame that represents a view of a scene using a ray tracing process, and the ray tracing process requires the determination of geometry that will be intersected by a ray, the programmable execution unit sends a message to a ray tracing acceleration data structure traversal circuit of the graphics processor, for the ray tracing acceleration data structure traversal circuit to perform a traversal of a ray tracing acceleration data structure for the scene to determine geometry for the scene that may be intersected by the ray. The ray tracing acceleration data structure traversal circuit then returns to the programmable execution unit an indication of geometry that may be intersected by the ray, and the programmable execution unit uses the indicated geometry to determine any geometry that is intersected by the ray.

Abstract: A method comprising the steps of generating a first representation and a second representation, where the first representation represents a first view of a computer-generated scene obtained from a first virtual camera and the second representation represents a second view of the computer-generated scene obtained from a second virtual camera. Each of the first and second representation comprises a plurality of rays which intersect with objects of the scene. A relationship is determined between a ray of the first representation and a ray of the second representation; which are grouped based on the relationship, to form a group of substantially similar rays. One or more of the groups of substantially similar rays are processed substantially simultaneously to produce a first a second rendered view of the computer-generated scene. The first the second rendered view are output to one or more display devices.

Abstract: A method of performing tone mapping in a stream of images (Fr1 . . . N) includes, for each image (FrN) in the stream: sparsely reading image data values (IDN) corresponding to the image (FrN) to provide sparse image data from a plurality of sparsely distributed positions (Pos1 . . . k) in the image (FrN); generating, based on the sparse image data, tone mapping parameters of a tone mapping algorithm (TMA) for each position in the image (FrN); each position in the image (FrN) including the sparsely distributed positions (Pos1 . . . k) and a plurality of further positions (PosF1 . . . j) in the image (FrN); reading the image data values (IDN) corresponding to the image (FrN) to provide image data from each position in the image (FrN); and tone mapping the image by mapping the image data from each position in the image (FrN) to adjusted image data using the generated tone mapping parameters.

Abstract: A method of operating a graphics processing system that generates “spacewarped” frames for display is disclosed. Primitive motion vectors are used to determine the motion of objects appearing in rendered application frames. The so-determined motion is then used to generate “spacewarped” versions of the rendered application frames.

Abstract: An image signal processor, comprising an input module for obtaining input data from a camera, whereby the camera is arranged to capture a representation of a real-world environment. The image signal processor further comprises at least one adjustment module for compressing the input data and producing compressed input data, and a localization and mapping module arranged to generate one or more data points from the compressed input data. The image signal processor also comprises an output module for outputting at least the one or more data points.

Abstract: The present disclosure provides an image processing apparatus and system which downscales an image which is generated from data provided by a sensor. The downscaled image is then analyzed to determine the location of one or more regions of interest in the image. The regions of interest can then be cropped from the original image and those cropped regions of interest processed by a computer vision engine.

Abstract: A method including streaming input image data representing an input frame of a video into temporary storage. Transformation data representing at least one transformation for application to the input image data is obtained. Ordering data indicating a variable order in which portions of output image data are to be generated is obtained, the ordering data being based on at least one characteristic of the input frame. The transformation data is used to identify portions of input image data to be processed to generate corresponding portions of output image data. The identified portions of input image data are processed to generate the corresponding portions of output image data in the order indicated by the ordering data.

Abstract: A method and apparatus for image processing, the method comprising obtaining input image data comprising a plurality of pixel intensity values representing a respective plurality of pixel locations, obtaining pixel location data identifying one or more pixel locations represented by compromised pixel intensity values, generating interpolated image data comprising improved pixel intensity values, storing improved image data comprising at least the interpolated image data, and detecting one or more further compromised pixel intensity values based on the improved image data.

Abstract: A method, processor and system of retaining dynamic range. The method comprises obtaining a vignetting correction mesh for image data. The method also comprises generating an intensity compression curve, the intensity compression curve comprising one or more segments, based on the vignetting correction mesh; and adjusting pixel values of a portion of the image data according to the intensity compression curve and vignetting correction mesh.

Abstract: A data processing system includes: a processor; a data interface for communication with a control unit, the processor being on one side of the data interface; internal storage accessible by the processor, the internal storage being on the same side of the data interface as the processor; and a register array accessible by the processor and comprising a plurality of registers, each register having a plurality of vector lanes. The storage is arranged to store control data indicating an ordered selection of vector lanes of one or more of the registers. The processor is arranged to, in response to receiving instruction data from a control unit, perform a swizzle operation in which data is selected from one or more source registers in the register array, and transferred to a destination register. The data is selected from vector lanes in accordance with control data stored in the internal storage.

Abstract: An arithmetic logic unit, comprising an addition unit for determining a sum of a first input and a second input; and a logarithmic addition unit for determining an output using the sum and a third input. The output is a multiply-accumulate output represented in a logarithmic domain when the first, second and third inputs are represented in the logarithmic domain.

Abstract: A method and apparatus for processing image data is provided. The method comprises storing accumulated image data, obtaining a new frame of image data, performing motion detection based at least on the new frame of image data, updating the accumulated frame of image data, and generating output image data. The motion detection identifies a pixel location in which motion is detected. For the pixel location identified by the motion detection, a pixel intensity value of the new frame of image data contributes more to a pixel intensity value representing the identified pixel location in the updated accumulated imaged data than to a pixel intensity value representing the identified pixel location in the output image data.

Abstract: When a programmable execution unit of a graphics processor is executing a graphics processing program to render a frame that represents a view of a scene using a ray tracing process, and the ray tracing process requires the determination of geometry that will be intersected by a ray, the programmable execution unit sends a message to a ray tracing acceleration data structure traversal circuit of the graphics processor, for the ray tracing acceleration data structure traversal circuit to perform a traversal of a ray tracing acceleration data structure for the scene to determine geometry for the scene that may be intersected by the ray. The ray tracing acceleration data structure traversal circuit then returns to the programmable execution unit an indication of geometry that may be intersected by the ray, and the programmable execution unit uses the indicated geometry to determine any geometry that is intersected by the ray.

Abstract: A display controller 93 in a data processing system includes a timewarp module (transformation circuitry) 100 that is operable to perform timewarp processing of a rendered frame 92 generated by a graphics processor (GPU) 91 for provision to a display panel 94. The timewarp module (transformation circuitry) 100 operates to transform an input surface 92 read by the display controller 93 based on received view orientation data to provide an appropriately “timewarped” transformed version of the input surface as an output transformed surface for display on the display 94.