Abstract: Method for texturing a 3D model of at least one scene (5), comprising: a) the meshing with surface elements (50; 55) of a point cloud (45) representing the scene, so as to generate the 3D model, each surface element representing an area of the scene, b) the unfolding of the 3D model for obtaining a 2D model formed of a plane mesh (60a; 60b) formed of polygons (65), each surface element corresponding to a single polygon, and vice versa, and c) for at least one, preferably all the surface elements, iv) the identification, from an image bank (40a; 40b), of the images representing the area of the scene and which have been acquired by a camera the image plane (72a-b) of which has a normal direction, in the corresponding acquisition position, forming an angle (?a-b) less than 10°, preferably less than 5°, better less than 3° with a direction normal (70) to the face of the surface element, v) the selection of an image (40a-b) from the identified images, and, vi) the association of a texture property with a corresp

Abstract: A 3D conversation system can facilitate 3D conversations in an augmented reality environment, allowing conversation participants to appear as if they are face-to-face. The 3D conversation system can accomplish this with a pipeline of data processing stages, which can include calibrate, capture, tag and filter, compress, decompress, reconstruct, render, and display stages. Generally, the pipeline can capture images of the sending user, create intermediate representations, transform the representations to convert from the orientation the images were taken from to a viewpoint of the receiving user, and output images of the sending user, from the viewpoint of the receiving user, in synchronization with audio captured from the sending user. Such a 3D conversation can take place between two or more sender/receiving systems and, in some implementations can be mediated by one or more server systems. In various configurations, stages of the pipeline can be customized based on a conversation context.

Abstract: A posture estimation device includes: a processor that: obtains detected information indicating a feature of a subject, wherein the feature is detected based on an image that is captured by an imager from a position where the subject is viewed from above, calculates a feature amount based on the obtained detected information, updates, based on a geometric relationship between the imager and the subject, a model parameter for estimating a posture of the subject by machine learning using the calculated feature amount in a time series, and estimates the posture of the subject using the updated model parameter.

Abstract: An aspect provides a computer-implemented method for constructing evaluation logic associated with an animation software package. The method comprises receiving at least one software module, the at least one software module including at least one evaluator; writing the at least one software module to at least one executable code object; and maintaining data for the at least one software module in a contiguous block of memory for use by the software module.

Abstract: A method and system for updates an occupancy map based on a first ray determined from a plurality of rays, as known as a super ray. The method of updating an occupancy map based on grids and octrees includes the step of generating a mapping line based on point clouds obtained from a sensor, determining a super ray by identifying a cell belonging to a plurality of cells forming the occupancy map and traversing an identical cell based on the generated mapping line, and updating the occupancy map by updating a cell through which the super ray corresponding to some of rays related to the plurality of cells forming the occupancy map passes.

Abstract: A method for generating a surround view (SV) image for display in a view port of an SV processing system is provided that includes capturing, by at least one processor, corresponding images of video streams from each camera of a plurality of cameras and generating, by the at least one processor, the SV image using ray tracing for lens remapping to identify coordinates of pixels in the images corresponding to pixels in the SV image.

Abstract: Embodiments are generally directed to affine motion compensation for current picture referencing. An embodiment of an apparatus includes one or more processors for processing of data; a memory for storage of data including video data; and an encoder for encoding of video data to generate encoded video data, wherein the encoder includes a component to provide affine motion compensation for current picture references in the video data.

Abstract: An information processing system for controlling movements of a character (200) in a virtual three-dimensional space, comprising movement control unit (231) that controls the movements of the character (200), and a switching determination unit (232) that determines switching of the movement of the character (200) by the movement control unit (231) between a three-dimensional movement in the virtual three-dimensional space and a movement in a predetermined surface (211) provided in the virtual three-dimensional space. The movement control unit (231) determines a speed of the character (200) after the switching on the basis of a speed of the character (200) before the switching when the switching is performed between the three-dimensional movement in the virtual three-dimensional space and the movement in the predetermined surface (211).

Abstract: Disclosed is a system for efficiently accessing a point cloud via a multi-tree deconstruction of the point cloud. The system may receive the point cloud, may differentiate different sets of data points from the point cloud using differentiation criteria, and may generate different trees with each tree having leaf nodes corresponding to one of the differentiated sets of data points and parent nodes defined according to commonality in values of two or more leaf nodes. The system may receive a request to render the 3D environment, load a first tree into memory, generate a first image from the first tree data points, flush the first tree from the memory, load a second tree into the memory, generate a second image from the second tree data points, and present a composite image by combining at least the first image with the second image.

Abstract: A social networking system provides a user interface for a sending user to send messages to a recipient user in association with a content item posted by the recipient user in the social networking system. The sending user views a content item posted by the recipient user, such as a photograph. The sending user posts a direct message to the recipient user related to the content item. The direct message is displayed to the sending user superimposed over the content item. Subsequent direct messages in the conversation are also displayed superimposed over the content item.

Abstract: The present invention teaches a real-time hybrid ray tracing system for non-planar specular reflections. The high complexity of a non-planar surface is reduced to low complexity of multiple small planar surfaces. Advantage is taken of the planar nature of triangles that comprise building blocks of a non-planar surface. All secondary rays bouncing from a given surface triangle toward object triangles keep a close direction to each other. A collective control of secondary rays is enabled by this closeness and by decoupling secondary rays from primary rays. The result is a high coherence of secondary rays.

Abstract: A property inspection service hosted on a web-based server system. The server system receives a list of physical addresses each corresponding to different parcels. For each address, the server system obtains multiple images including overhead images and perspective view images. A first trained model analyzes selected overhead images individually to identify one or more building structures. A second trained model analyzes selected perspective view images individually to identify a primary building structure. A third trained model analyzes the selected overhead images and the perspective view images together in an integrated approach to identify attributes associated with identified building structure. A digital report is generated as a graphical user interface configured to display the selected images and the attributes associated the identified building structure.

Abstract: A three-dimensional image display system includes: a vapor generating component, a rotating component, a shell, a lens component, a support component and a display device; where the vapor generating component is configured to control an vapor ejection from an air outlet; the rotating component is configured to drive a rotating disk of the rotating component to rotate at a preset refresh frequency and control a nozzle on the rotating disk to eject vapor to form a vapor column; the display device includes a plurality of columns of pixel units, and one column of pixel units corresponding to the vapor column is configured to display three-dimensional image data when receiving the three-dimensional image data; the lens component includes a plurality of lenses, and each lens is configured to focus light emitted by a corresponding pixel unit, to form a real image at an image plane at the vapor column.

Abstract: An image processing method and an information processing device are provided. The information processing device may include a processor, which may be configured to: construct a three-dimensional face model based on a face object in a two-dimensional image; determine a correspondence between the constructed three-dimensional face model and the face object in the two-dimensional image; determine, based on the correspondence, an area of interest of a key point in the two-dimensional image using an area of interest near a corresponding key point in the three-dimensional face model; and extract an image feature from the determined area of interest in the two-dimensional image as an image feature of the key point.

Abstract: Positioning a handle in a head mounted display system, and a head mounted display system. A wireless radio frequency master device is used on a head mounted device in the head mounted display system to perform operations of pairing with a wireless radio frequency slave device of a first handle and a wireless radio frequency slave device of a second handle. An electromagnetic wave receiver is used to receive electromagnetic waves emitted by an electromagnetic wave emitter of the first handle and an electromagnetic wave emitter of the second handle and generate an induced electromotive force. And, calculating position and posture information corresponding to the first handle and information of position and posture corresponding to the second handle respectively, wherein the position and posture information includes position translation information and direction rotation information when the wearer wears the first handle or the second handle.

Abstract: Technologies for analyzing various features detected in a face detected in an image. Such features may include at least the eyes, eyebrows, node, and mouth of a face. Such analyzing may include scoring aspects of these features. Such scores may be weighted. The analysis may be used to determine expressions and/or poses of the face, as well as indicate if the face is smiling, frowning, or neutral. An overall quality score for the face may also be determined and provided based on the aforementioned analysis as well as whether or not the face is near an edge of the image or cut-off in the image. Finally, a face signature may be determined that uniquely identifies the face, at least within the scope of the analyzed features. Such face signatures may be used to detect a similar face in other images.

Abstract: Embodiments are generally directed to methods and apparatuses for compression of graphics processing commands.

Abstract: A real-time video exploration (RVE) system that allows users to pause, step into, and explore 2D or 3D modeled worlds of scenes in a video. The system may leverage network-based computation resources to render and stream new video content from the models to clients with low latency. A user may pause a video, step into a scene, and interactively change viewing positions and angles in the model to move through or explore the scene. The user may resume playback of the recorded video when done exploring the scene. Thus, rather than just viewing a pre-rendered scene in a movie from a pre-determined perspective, a user may step into and explore the scene from different angles, and may wander around the scene at will within the scope of the model to discover parts of the scene that are not visible in the original video.

Abstract: One embodiment of the invention provides a pattern generation device includes a light source, a first HPDLC cell, and a second HPDLC cell. The first HPDLC cell is disposed downstream of a light path of the light source and contains a first phase modulation pattern. The second HPDLC cell is disposed downstream of a light path of the first HPDLC cell and contains a second phase modulation pattern.

Abstract: Methods, systems, and techniques for generating a new anatomy use a processor to obtain a skin mesh of the new anatomy that is in correspondence with a skin mesh of a template anatomy; after obtaining the skin mesh, transfer a fascia mesh of the template anatomy to the new anatomy; and after the fascia mesh is transferred, generate a fat displacement field defining fat of the new anatomy. The displacement field includes multi-dimensional displacement vectors, and each of the displacement vectors relates a vertex of the skin mesh of the new anatomy to a corresponding vertex of the fascia mesh of the new anatomy. A new anatomy may also be generated by interpolating from anatomies in a database.

Abstract: Systems and methods for evaluating changes in terrain topography over time are provided. A first point cloud corresponds to the terrain topography during a first time period. A second point cloud corresponds to the terrain topography during a second time period. One or more processors collectively execute instructions to: for each point in the first point cloud, determine a point plane; align the first and second point clouds based on a plurality of plane offset distances; for each point in the aligned second point cloud, calculate a normal direction; for each point in the aligned second point cloud, identify one or more corresponding points in the aligned first point cloud; and generate a third point cloud representing topographical differences. The first point cloud can be divided into a plurality of grid cells and a plurality of graphics processing cores can execute parallel point processing based on the plurality of grid cells.

Abstract: The disclosed systems and methods provide for generating real-time egress plans for users in a building, based on the users' current locations. As the users' current locations change, egress plans associated with the users can be dynamically modified in real-time. The egress plans can also be generated, modified, and/or trained based on inputted information about the user. The disclosed technology can include a mobile application for presenting, in a centralized interface, information about user-specific egress plans, training the user for different emergency scenarios, improving or changing features in the building to improve safety, and user profiles. The mobile application can include training simulation games to help prepare the users to safely egress during an emergency. The disclosed technology can also predict building component and structure emergency risk levels. The disclosed technology can also designate zones in the building based on possible egress routes.

Abstract: A Near-Eye-Display (NED) devices that translates combinations of user gaze direction and predetermined facial gestures into user input instructions. The NED device includes an eye tracking system and a display that renders computer-generated images within a user's field-of-view. The eye tracking system may continually track the user's eye movements with a high degree of accuracy to identify specific computer-generated images that a user is focused on. The eye tracking system may also identify various facial gestures such as, for example, left-eye blinks and/or right-eye blinks that are performed while the specific computer-generated images are being focused on. In this way, NED devices are enabled to identify combinations of user gaze direction and predetermined facial gestures and to translate these identified combinations into user input instructions that correspond to specific computer-generated images.

Abstract: There is provided an image processing apparatus and an image processing method by which three-dimensional data can be generated with high accuracy on the basis of two-dimensional image data and depth image data. A coordinate transformation data generation unit generates, on the basis of two-dimensional image data of a first viewpoint group and two-dimensional image data of a second viewpoint group, coordinate transformation data for converting a three-dimensional position in a first three-dimensional coordinate system of the first viewpoint group into a three-dimensional position in a second three-dimensional coordinate system of the second viewpoint group.

Abstract: A community mapping platform may receive an image that depicts a community layout of a community and may process, using a computer vision model, the image to identify a unit, of the community, that is depicted in the image (e.g., based on identifying a text string and/or a polygon in the image). The community mapping platform may determine sets of community geographical coordinates for a set of reference locations of the community and may map the sets of community geographical coordinates to corresponding reference pixel locations of the image. The community mapping platform may determine, using a geographical information system, unit geographical coordinates of the unit based on the reference pixel locations and may perform an action associated with the unit geographical coordinates.

Abstract: Disclosed is an electronic device that includes a display that outputs execution screens of a plurality of applications, a memory that stores the plurality of applications, and a processor electrically connected with the display and the memory. The processor retrieves a history of one or more applications among the plurality of applications that were previously executed in the electronic device, in response to a user input detected by the electronic device and outputs the history on the display based on information about the one or more applications and information about layouts of execution screens of the one or more applications. If at least one of the one or more applications is selected from the history, the processor outputs an execution screen of the selected application on the display according to the corresponding layout.

Abstract: A system initializes a set of calibrated images with known 3D pose relative to a 3D building information model (BIM) to be anchor images, detects features within images of unknown position and orientation, and determines matches with features of the calibrated images. The system determines a subset of the images that have at least a threshold number of matching features, selects an image from the subset of the images having the largest number of matching features, and executes a reconstruction algorithm using the image and the anchor images to calibrate the image to the BIM and generate an initial 3D point cloud model. The system repeats the last steps to identify a second image from the subset and perform, starting with the initial 3D point cloud model and using the second image, 3D reconstruction to generate an updated 3D point cloud model that is displayable in a graphical user interface.

Abstract: An information processing device including a display control unit that controls, when recognition information related to recognition based on sensing of a real object includes first recognition information, shielding display representing shielding of a virtual object by the real object such that the shielding display presents a first boundary representation at a boundary between the virtual object and the real object or at a position near the boundary, and controls, when the recognition information includes second recognition information different from the first recognition information, the shielding display such that the shielding display presents a second boundary representation different from the first boundary representation at the boundary or at a position near the boundary.

Abstract: A system is comprised of one or more processors coupled to memory. The one or more processors are configured to receive image data based on an image captured using a camera of a vehicle and to utilize the image data as a basis of an input to a trained machine learning model to at least in part identify a distance of an object from the vehicle. The trained machine learning model has been trained using a training image and a correlated output of an emitting distance sensor.

Abstract: Disclosed herein is a web-based videoconference system that allows for video avatars to navigate within the virtual environment. The system has a presented mode that allows for a presentation stream to be texture mapped to a presenter screen situated within the virtual environment. The relative left-right sound is adjusted to provide sense of an avatar's position in a virtual space. The sound is further adjusted based on the area where the avatar is located and where the virtual camera is located. Video stream quality is adjusted based on relative position in a virtual space. Three-dimensional modeling is available inside the virtual video conferencing environment.

Abstract: A method and corresponding system for reconstructing the surface geometry of a three-dimensional object is disclosed. The system comprises a cluster of heterogeneous sensors, including a two-dimensional high-resolution camera and a three-dimensional depth camera, and a turntable operable to rotate incrementally. In operation, the turntable is rotated to first and second positions and two-dimensional and three-dimensional data sets are obtained using the two-dimensional high-resolution camera and the three-dimensional depth camera. Corresponding features from the two-dimensional data sets are identified and used to identify the same corresponding features in the three-dimensional data sets. The three-dimensional corresponding features are used to calculate a three-dimensional homography, which is used to align the three-dimensional data sets. Following alignment, a three-dimensional mesh is generated from the aligned data sets.

Abstract: A telepresence robot may include a drive system, a control system, an imaging system, and a mapping module. The mapping module may access a plan view map of an area and tags associated with the area. In various embodiments, each tag may include tag coordinates and tag information, which may include a tag annotation. A tag identification system may identify tags within a predetermined range of the current position and the control system may execute an action based on an identified tag whose tag information comprises a telepresence robot action modifier. The telepresence robot may rotate an upper portion independent from a lower portion. A remote terminal may allow an operator to control the telepresence robot using any combination of control methods, including by selecting a destination in a live video feed, by selecting a destination on a plan view map, or by using a joystick or other peripheral device.

Abstract: Provided is a method for matching a virtual scene of a remote scene with a real scene for augmented reality and mixed reality. Multiple coordinate systems are established and a position relationship between the multiple coordinate systems is determined. A position of a point cloud scene in the near-side environmental space and the position of the near-side virtual scene are determined in the near-side environmental space through real marks, so as to realize the high-precision matching and positioning for augmented reality and mixed reality. Based on the position of objects marked in the real space, the method realizes adaptive and accurate positioning of the virtual objects in the augmented reality and mixed reality by overcoming spatial barriers. The scene in the virtual space is accurately superimposed into the near-side environmental space.

Abstract: An example system disclosed herein includes a camera to: capture a first image set of a first view of an object when the camera is in a first position, the first image set including first infrared data and first RGB data; capture a second image set of a second view of the object when the camera is in a second position, the second image set including second infrared data and second RGB data; and capture a third image set of a third view of the object when the camera is in a third position, the third image set including third infrared data and third RGB data.

Abstract: In an example embodiment, techniques are provided for 3D object detection by detecting objects in 2D (as 2D bounding boxes) in a set of calibrated 2D images of a scene, matching the 2D bounding boxes that correspond to the same object and reconstructing objects in 3D (represented as 3D bounding boxes) from the corresponding, matched 2D bounding boxes. The techniques may leverage the advances in 2D object detection to address the unresolved issue of 3D object detection. If sparse 3D points for the scene are available (e.g., as a byproduct of SfM photogrammetry reconstruction) they may be used to refine the 3D bounding boxes (e.g., to reduce their size).

Abstract: To provide a control device, control method, and surgical system that can further improve safety.

Abstract: A method for moving and orienting an object in a virtual reality or augmented reality environment that uses a movement tool with multiple states that correspond to the actions that a user may take to manipulate the object. The movement tool may have a stored position and orientation that are applied directly to the object without the need for user input; if these parameters are not stored, the movement tool may enter a moving or placing state, and/or an orientation state where the user can set the position or orientation, respectively. Additional movement tool states may include a rotation state and a translation state. State-specific guides or controls may be shown in certain states of the movement tool. These tools may enable a user to perform accurate and intuitive actions to move, scale or rotate an object in an n-dimensional space with millimeter precision.

Abstract: An electronic device and a method of operating the same are provided. The electronic device includes a camera module, a display, a memory, and a processor configured to be operatively connected to the camera module, the display, and the memory, wherein the processor is further configured to display a preview image obtained from the camera module on the display, to recognize an object from the preview image, to detect a drawing input based on the object, to generate a graphic element by the detected drawing input, and to display the graphic element to correspond to the object by tracking the object. In addition, various embodiments are possible.

Abstract: A model simplification method is provided. The model simplification method includes: constructing a surrounding body to surround a model, wherein the model includes at least one primitive and a plurality of vertexes; drawing the model and the surrounding body to at least one rendering surface by respectively taking each of the plurality of vertexes as an eye-position; determining whether the surrounding body drawn on the rendering surface by taking a current vertex of the plurality of vertexes as the eye-position is occluded to decide whether to mark the current vertex as an invisible vertex; and eliminating a current primitive from the model when all vertexes of the current primitive of the at least one primitive are marked as the invisible vertex.

Abstract: Embodiments disclose a method, apparatus and a computer readable storage medium for providing cloud platform virtual assets. The method includes: generating virtual asset configuration information and a virtual asset model, and sending the virtual asset configuration information and the virtual asset model to a cloud platform; obtaining asset measurement data of a real device and obtaining asset simulation data from a simulation side of the real device, and filtering the asset measurement data and the asset simulation data based on the virtual asset configuration information provided by the cloud platform and sending the filtered data to the cloud platform; providing the virtual asset model and the filtered data from the cloud platform. The embodiments relate virtual digital world to the real physical world and seamlessly integrate the simulation data with the measurement data.

Abstract: A three-dimensional (3D) display apparatus is provided. The 3D display apparatus includes a display panel configured to output pixel values that respectively correspond to a preset number of viewpoints, and an optical layer that is provided in front of or behind the display panel and that is configured to adjust directions of rays output from the display panel or to provide light to the display panel so that the rays diverge.

Abstract: A method in constructing a model of a scenery comprises: receiving (200) a plurality of images depicting the scenery, wherein each image is acquired by a camera (104) from a position at a rotational angle; creating (202) a plurality of sub-models, wherein each sub-model is created by: selecting (400) a basis image; determining (402) images related to the basis image; and determining (404) the sub-model based on the basis image and the related images, wherein the sub-model defines relative positions and rotational angles of the camera (104) for the basis image and the related images and the sub-model further defines three-dimensional structures of objects depicted in the plurality of images; and separately merging (204) the defined relative positions and rotational angles of cameras (104) for the plurality of sub-models.

Abstract: An application for use with a mobile computing device is described that enables group members of a group activity to view the positions of each member in one or more formations for the group activity. The application enables the user to select a formation for viewing and practicing in any location, whether indoors or outdoors and with or without other group members of the group activity. The application allows the user to toggle between a top-down view and an augmented reality view. The augmented reality view enables a user to view graphical indicators of each position of the user, whereby the graphical indicators are superimposed on a user's computing device in the real user environment. The augmented reality view provides a user with a better understanding of his or her positions in a real-world environment.

Abstract: An example augmented reality (AR) system can include a frame, a lens attached to the frame, and a plurality of cameras attached to the frame. The cameras can be configured to record a real-time image. Optionally, the real-time image can include a portion of a subject's body and/or one or more surgical instruments. Additionally, the AR system can include a plurality of inertial measurement units, where a respective inertial measurement unit is attached to each respective camera. Optionally, the AR system can be configured to display image data (e.g., medical image data) registered and superimposed on the real-time image as seen by the user of the AR system.

Abstract: A processing device receives first intraoral scan data of a first segment of a dental site and second intraoral scan data of a second segment of the dental site that does not stitch to the first intraoral scan data of the first segment of the dental site. The processing device generates a first virtual model of the first segment using the first intraoral scan data, and further generates a second virtual model of the second segment using the second intraoral scan data. The processing device arranges a spatial relationship of the first virtual model and the second virtual model.

Abstract: A virtual meeting is carried out between at least one first person and one second person, in which the virtual meeting is displayed in the form of a first virtual surrounding area by use of a first display device assigned to the first person and in the form of a second virtual surrounding area by use of a second display device assigned to the second person. The first person may be disposed in a moving vehicle whose vehicle movement is sensed and the representation of the first virtual surrounding area is selected in accordance with the sensed movement of the vehicle. The second person may be disposed in a reference system which differs from the vehicle and whose movement is sensed, and the representation of the second virtual surrounding area is selected in accordance with the sensed movement of the reference system.

Abstract: An imaging system and a method for producing extended-reality images for a display apparatus. The imaging system includes camera and processor. The processor is configured to: control camera to capture image of real-world environment; analyse captured image to identify first image segment representing input device and to determine location of at least one actionable area of input device in first image segment; determine at least one functional element to be presented for the actionable area, the functional element being indicative of at least one of: functionality of the at least one actionable area, status of the at least one actionable area; and process captured image to generate extended-reality image in which the functional element is virtually superimposed over the actionable area of input device or a virtual representation of the actionable area of input device.

Abstract: According to an aspect of the present invention, provided is an image processing device comprising a saturation value acquisition unit configured to acquire a saturation value of a target pixel or a saturation value of a target small area including a target pixel and peripheral pixels around the target pixel, and a correction unit configured to correct the target pixel so that a corrected gradation characteristic obtained by correcting the target pixel matches a gradation characteristic synthesized by mixing a color gradation characteristic and a monochrome gradation characteristic at a predetermined mixing ratio based on the saturation value, wherein assuming that the saturation value is c, and the mixing ratio of the color gradation characteristic is W, a value of W is represented by variable c as a relationship W=f(c) and satisfies a following condition.

Abstract: A system and a method are disclosed for ray tracing in a pipeline of a graphic processing unit (GPU). It is determined whether a ray bounce of a first ray intersects a first primitive that is the closest primitive intersected by the ray bounce. The first ray is part of a first group of rays being processed by a first single-instruction-multiple-data (SIMD) process. The first ray is assigned by a sorting or binning unit to a second group of rays based on the intersection of the first primitive. The second group of rays is processed by a second SIMD process. The first ray is assigned to the second group of rays based on a material identification of the first primitive, an identification of the first primitive intersected by the ray bound of the first ray, a pixel location, and a bounce number of the ray bounce intersecting the first primitive.

Abstract: A rendering optimisation identifies a draw call within a current render (which may be the first draw call in the render or a subsequent draw call in the render) and analyses a last shader in the series of shaders used by the draw call to determine whether the last shader samples from the one or more buffers at coordinates matching a current fragment location. If this determination is positive, the method further recompiles the last shader to replace an instruction that reads data from one of the one or more buffers at coordinates matching a current fragment location with an instruction that reads from the one or more buffers at coordinates stored in on-chip registers.