Abstract: A method and system are provided for hybrid streaming of media content such as video for a computer-based game. In some implementations, a background media content stream includes a background video rendered on a server. The background media content stream is received at a client device. The client device renders one or more three-dimensional objects and forms a composite media stream by combining the background media content stream and the one or more three-dimensional objects. The composite media stream can be output to a display or other external system.

Abstract: A graphics processing system includes a tiling unit configured to tile a first view of a scene into a plurality of tiles, a processing unit configured to identify a first subset of the tiles that are associated with regions of the scene that are viewable in a second view, and a rendering unit configured to render to a render target each of the identified tiles.

Abstract: The present concepts relate to shadow culling when rendering a 3D computer graphics virtual world. A depth buffer may be rendered from the perspective of a camera, and the depth buffer can be used to generate a hit map, which can be used to determine which objects in the world will need shadow tests. When shadow maps are generated by rendering multiple cascades from the perspective of a light, rather than including all objects in a particular cascade into the shadow map, the pixels in the hit map corresponding to an object are checked to determine whether a shadow test will be needed for the object. If the object will not contribute to the main scene, then the object is excluded from the shadow map, thus saving GPU processing resources.

Abstract: A display device includes a display, a bezel disposed along a periphery of the display, a touch sensor disposed inward of the bezel and configured to receive, from a user, a first touch input at a touch location of the touch sensor, and a processor configured to control the display to display a user interface at a first location of the display. The processor is further configured to, in response to the first touch input being received while the user interface is displayed at the first location, determine a user location of the user, based on the touch location at which the first touch input is received, and control the display to move the user interface that is displayed, to a second location of the display, the second location corresponding to the user location that is determined.

Abstract: A method, apparatus and computer program product access a video-based point cloud compression coded bitstream. The point cloud compression coded bitstream corresponds to a non-timed video-based point cloud compression representation that comprises one or more video point cloud compression units. The method, apparatus and computer program product encapsulate the one or more video point cloud compression units as one or more video point cloud compression unit items. The method, apparatus and computer program product also cause storage of the one or more video point cloud compression unit items in a file.

Abstract: In one embodiment, a method includes accessing a distortion mesh defined in a 3D space by a plurality of mesh coordinates that are respectively associated with a plurality of predetermined points in a screen representation, where each mesh coordinate specifies a trajectory for a ray cast from the associated predetermined point into the 3D space; determining a sampling point within the screen representation; selecting a set of mesh coordinates from the plurality of mesh coordinates based on proximities between the sampling point and the predetermined points associated with the set of mesh coordinates; computing a sampling trajectory for the sampling point based on the selected set of mesh coordinates; casting a ray into the 3D space using the sampling trajectory; computing an intersection location between the cast ray and an object in the 3D space; and determining a color value for the sampling point based on the intersection location.

Abstract: Systems, methods, devices, and non-transitory media of various embodiments enable prioritization of requests for hierarchical level of detail (HLOD) content over a communications network. Various embodiment methods may reduce load time of nodes in the HLOD data structure, such as nodes in the HLOD that may be deemed important, compared to the load time achieved in current methods. Various embodiments may provide methods for prioritizing requests for nodes.

Abstract: A method and system is provided for culling hidden objects in a tile-based graphics system before they are indicated in a display list for a tile. A rendering space is divided into a plurality of regions which may for example be a plurality of tiles or a plurality of areas into which one or more tiles are divided. Depth thresholds for the regions, which are used to identify hidden objects for culling, are updated when an object entirely covers a region and in dependence on a comparison between a depth value for the object and the depth threshold for the region. For example, if the depth threshold is a maximum depth threshold, the depth threshold may be updated if an object entirely covers the tile and the maximum depth value of the object is less than the maximum depth threshold.

Abstract: The present disclosure relates to methods and apparatus for graphics processing. An example method generally includes receiving, at a graphics processing unit (GPU), a plurality of commands corresponding to a plurality of draws across a frame, each of the plurality of commands indicating a depth test direction with respect to a low-resolution depth (LRZ) buffer for the corresponding draw. The method generally includes maintaining, at the GPU, a LRZ status buffer to store a corresponding depth test direction for a first command in time of the plurality of commands processed by the GPU. The method generally includes disabling, at the GPU, use of the LRZ buffer for depth testing for any of the plurality of commands remaining unprocessed after processing a command of the plurality of commands having a different depth test direction than the corresponding depth test direction stored in the LRZ status buffer.

Abstract: An image processing method and apparatus. The image processing method includes: obtaining encoded data of a first region and a neighboring region neighboring to the first region in a two-dimensional planar image, where the two-dimensional planar image is an image obtained by mapping a spherical panorama image, and the first region and the neighboring region have an overlapping region; determining a pixel value of a pixel in an image of the first region; determining a pixel value of a pixel in an image of the neighboring region; and determining a target pixel value of a pixel in the overlapping region based on the pixel value of the pixel of the first region in the overlapping region and the pixel value of the pixel of the neighboring region in the overlapping region.

Abstract: There is provided an image processing apparatus and an image processing method that are capable of improving the accuracy of a depth image of a 3D model. A depth image generation unit generates a depth image of a plurality of viewpoints for each object included in a 3D model. The present disclosure is applicable to, for example, an encoding device or the like configured to generate a color image and a depth image of each object of each of a plurality of viewpoints on the basis of 3D data of a 3D model, generate an encoded stream by encoding the images, and generate object range information indicating the range of each object.

Abstract: Systems and methods are described that obtain depth data associated with a scene captured by an electronic device, obtain location data associated with a plurality of physical objects within a predetermined distance of the electronic device, generate a plurality of augmented reality objects configured to be displayed over a portion of the plurality of physical objects, and generate a plurality of proximity layers corresponding to the at least one scene, wherein a respective proximity layer is configured to trigger display of the auxiliary data corresponding to AR objects associated with the respective proximity layer while suppressing other AR objects.

Abstract: Embodiments described herein provide for a technique to improve the culling efficiency of coarse depth testing. One embodiment provides for a graphics processor that includes a depth pipeline that is configured to perform a method to track a history of source fragments that are tested against a destination tile. When a combination of partial fragments sum to full coverage, the most conservative source far depth value is used instead of the previous destination far depth value.

Abstract: The present disclosure relates to methods and apparatus for graphics processing. In some aspects, the apparatus can determine a plurality of sub-primitives corresponding to one or more primitives in an image. The apparatus can also determine visibility information for each of the sub-primitives. The visibility information can include information regarding whether the sub-primitive is visible. Further, the apparatus can identify one or more of the sub-primitives as visible based on the visibility information. The apparatus can also determine a sub-primitive visibility stream including the sub-primitives identified as visible. Additionally, the apparatus can render at least one of the sub-primitives identified as visible in the sub-primitive visibility stream. The apparatus can also identify at least one of the sub-primitives as not visible based on the determined visibility information. Moreover, the apparatus can determine to skip rendering the at least one of the sub-primitives identified as not visible.

Abstract: Briefly, in accordance with one or more embodiments, a processor performs a coarse depth test on pixel data, and performs a final depth test on the pixel data. Coarse depth data is stored in a coarse depth cache, and per pixel depth data is stored in a per pixel depth cache. If a result of the coarse depth test is ambiguous, the processor is to read the per pixel depth data from the per pixel depth cache, and to update the coarse depth data with the per pixel depth data if the per pixel depth data has a smaller depth range than the coarse depth data.

Abstract: Methods and systems for use of a reference image to detect a road obstacle are described. A computing device configured to control a vehicle, may be configured to receive, from an image-capture device, an image of a road on which the vehicle is travelling. The computing device may be configured to compare the image to a reference image; and identify a difference between the image and the reference image. Further, the computing device may be configured to determine a level of confidence for identification of the difference. Based on the difference and the level of confidence, the computing device may be configured to modify a control strategy associated with a driving behavior of the vehicle; and control the vehicle based on the modified control strategy.

Abstract: A graphics processor includes a rasteriser, an early depth tester, a renderer, a late depth tester, and a depth test data buffer that stores depth data values for use by the early and late depth testers. When a fragment is to undergo an early depth test to update the depth buffer, it is first determined whether the fragment should undergo the early depth test to update the depth buffer without waiting for any other fragment to undergo a depth test, or whether the result of a late depth test on a fragment that is still to undergo a late depth test should be awaited before performing a depth test to update the depth buffer on the fragment.

Abstract: An apparatus comprises a store (201) storing images corresponding to different positions and viewing directions for a scene, and associated position parameter vectors for the images where the vector for an image comprises data indicative of a viewing position and a viewing direction. A receiver (205) receives a viewing position parameter vector from a remote client (101). A selector (207) selects a set of images in response to a comparison of the viewing position parameter vector and the associated position parameter vectors. An image synthesizer (209) generates an image from the set of images. A data generator (215) generates a reference position parameter vector for the synthesized image indicating a viewing position and direction for the synthesized image. An image encoder (211) encodes the synthesized image and an output generator (213) generates an output image signal comprising the encoded synthesized image and the reference position parameter vector.

Abstract: Systems and techniques for automatic object replacement in an image include receiving an original image and a preferred image. The original image is automatically segmented into an original image foreground region and an original image object region. The preferred image is automatically segmented into a preferred image foreground region and a preferred image object region. A composite image is automatically composed by replacing the original image object region with the preferred image object region such that the composite image includes the original image foreground region and the preferred image object region. An attribute of the composite image is automatically adjusted.

Abstract: Systems and methods for processing primitive fragments in a rasterization phase of a graphics processing system wherein a rendering space is subdivided into a plurality of tiles. The method includes receiving a plurality of primitive fragments, each primitive fragment corresponding to a pixel sample in a tile; determining whether a depth buffer read is to be performed for hidden surface removal processing of one or more of the primitive fragments; sorting the primitive fragments into a priority queue and a non-priority queue based on the depth buffer read determinations; and performing hidden surface removal processing on the primitive fragments in the priority and non-priority queues wherein priority is given to the primitive fragments in the priority queue.

Abstract: A graphics processor that performs early depth tests for primitives in respect of patches of a render output, and depth tests for sampling positions of the render output, maintains a per patch depth buffer that stores depth values for patches for use by the patch early depth test and a per sample depth buffer. When processing of a render output is stopped before the render output is finished, the per sample depth values in the per sample depth buffer are written to storage so that those values can be restored, but the per patch depth value information in the per patch depth buffer is discarded. Then, when processing of the render output is resumed, the per sample depth buffer values are loaded into a per sample depth buffer, and the loaded per sample depth buffer values are also used to restore the per patch depth buffer.

Abstract: A global illumination calculation method and apparatus is provided. The method includes: acquiring at least one of SDF information and illumination information corresponding to each of preselected pixels displayed on a screen, and the SDF information and illumination information corresponding to each pixel are stored in a two-dimensional map formed by mapping a three-dimensional map; and performing global illumination calculation according to at least one of the SDF information and the illumination information corresponding to each pixel. The method solves technical problems of global illumination calculation methods in the related art that a large amount of hardware resources are consumed and the presented image effects are not ideal enough.

Abstract: A graphics rendering system is disclosed for generating and streaming graphics data of a 3D environment from a server for rendering on a client in 2.5D. 2D textures can be transmitted in advance of frames showing the textures. Data transmitted for each frame can include 2D vertex positions of 2D meshes and depth data. The 2D vertex positions can be positions on a 2D projection as seen from a viewpoint within the 3D environment. Data for each frame can include changes to vertex positions and/or depth data. A prediction system can be used to predict when new objects will be displayed, and textures of those new objects can be transmitted in advance.

Abstract: Methods, systems, and computer-readable storage media for a storage device to, upon receiving a command from a computing host, determine whether or not the command includes location information targeting a particular portion of a NVM of the storage device, the location information having been retrieved by the computing host from a shadow map and included with the command. Upon determining that the command includes location information, the command is processed by the storage device using the included location information. Upon determining that the command does not include location information, the storage device determines the particular portion of the NVM targeted by the command based on a map stored in a memory of the storage device before processing the command.

Abstract: An electronic apparatus and method is provided for shape-refinement of a triangular 3D mesh using a modified Shape from Shading (SFS) scheme. The electronic apparatus generates a flat two-dimensional (2D) mesh based on an orthographic projection of an initial three-dimensional (3D) triangular mesh on an image plane that includes a plurality of square grid vertices. The electronic apparatus estimates a final grid depth value for each square grid vertex of the flat 2D mesh based on a modified SFS scheme. The modified SFS scheme corresponds to an objective relationship among a reference grid image intensity value, an initial grid depth value, and a grid albedo value for each square grid vertex of the plurality of square grid vertices. The electronic apparatus estimates a final 3D triangular mesh based on the initial 3D triangular mesh and the estimated final grid depth value.

Abstract: 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.

Abstract: A low power driving method includes receiving a signal for a sub control module from a main control module when an electronic device enters a low power mode. The low power driving method also includes transmitting display data to a display driving module in response to the signal.

Abstract: A breast imaging device for rotating a radiation detection unit configured to detect radiation irradiated from a radiation generation unit configured to generate the radiation with the radiation detection unit and the radiation generation unit facing each other includes a ray sum image generation unit configured to generate a ray sum image based on an addition value of at least one pixel value in a visual line direction from volume data reconstructed from a projection image output from the radiation detection unit, a maximum intensity projection image generation unit configured to generate a maximum intensity projection image based on the maximum pixel value in the visual line direction from the volume data, and a synthesizing unit configured to synthesize the ray sum image and the maximum intensity projection image.

Abstract: A graphics processing system comprising: a tiling unit configured to tile a first view of a scene into a plurality of tiles; a processing unit configured to identify a first subset of the tiles that are associated with regions of the scene that are viewable in a second view; and a rendering unit configured to render to a render target each of the identified tiles.

Abstract: An information processing device includes a data input unit that receives time-series data from an external device, a first processing unit that adds time information to data acquired from the data input unit and processes data to which the time information has been added, on a real-time operating system that performs a process within a specified time period, and a second processing unit that processes data to which the time information has been added, on a non-real-time operating system.

Abstract: A social game capable of adding or improving unexpectedness, dramatic impact, and taste when a reward is provided to a player, and hence capable of raising the player's motivation to participate in or continue the game. A unit for storing information related to a game in which multiple players can participate stores a reward providing condition, rewards, and reward box information, and a control unit for accessing information related to the game, performing computation on the game, and displaying images of the game on terminal devices operated by players allocates at least one reward out of the rewards to the reward box, determines whether the reward providing condition is met based on match-up situations or match-up results between players and first game characters in the game, and displays, on the terminal devices, a screen for providing the reward to players based on the determination results.

Abstract: This application relates generally to augmenting images and videos with dynamic object compositing, and more specifically, to generating synthetic training data to train a machine learning model to automatically augment an image or video with a dynamic object. The synthetic training data may contain multiple data points from thousands of simulated dynamic object movements within a virtual environment. Based on the synthetic training data, the machine learning model may determine the movement of a new dynamic object within new virtual environment.

Abstract: An image processing apparatus includes a setting unit configured to set a virtual light source for a captured image; a brightness correction unit configured to correct brightness of a partial region of an object using the virtual light source set by the setting unit; an attribute detection unit configured to detect an attribute of the partial region; a glossy component generation unit configured to generate a glossy component that is to be applied to the partial region, according to the attribute of the partial region detected by the attribute detection unit; and a glossy appearance correction unit configured to correct a glossy appearance of the partial region using the glossy component generated by the glossy component generation unit.

Abstract: A virtual reality (VR) based driving simulation system and method provides hazard perception training and testing. Some embodiments use a personal computing device (e.g., smartphone), a head-mounted VR headset, and a Bluetooth-connected push button keypad or other user input device. An immersive, 3D simulator enables users to experience and learn from hazardous scenarios without risking injury. Performance by a user in perceiving a hazard is compiled as a metric in a user profile stored on a server, and continued training and testing can be conducted with updated scenarios supplied by the server in accordance with the metric associated with a user.

Abstract: According one embodiment, there is provided a drawing method, that comprises: when at least part of a first surface and at least part of a second surface are practically congruent to each other in a three-dimensional coordinate system, assigning each of a first drawing pattern related to the first surface and a second drawing pattern related to the second surface to any one of more than one unit drawing area forming the at least part of the first surface or the at least part of the second surface, drawing the more than one unit drawing area by using the first drawing pattern and the second drawing pattern each assigned to any one of the more than one unit drawing area, and thereby drawing the at least part of the first surface or the second surface.

Abstract: A computer implemented method for warping virtual content includes generating warped virtual content by transforming source virtual content. The method also includes determining whether a memory location corresponding to an X, Y location of the warped virtual content in an output frame of reference is occupied by pre-existing virtual content. The method further includes storing the warped virtual content in the memory location if the memory location is not occupied. Moreover, the method includes comparing respective Z locations of the warped virtual content and the pre-existing virtual content to identify virtual content with a Z location closer to a viewing location if the memory location is occupied. The method also includes storing the warped virtual content in the memory location corresponding to the X, Y location if a Z location of warped virtual content is closer to the viewing location than a pre-existing Z location of pre-existing virtual content.

Abstract: An information processing apparatus includes one or more memories storing instructions, and one or more processors executing the instructions to determine, among a plurality of captured images obtained by a plurality of image capturing apparatuses, a display target image related to a virtual viewpoint image, based on a position of a virtual viewpoint and a view direction from the virtual viewpoint, the virtual viewpoint image being generated based on the display target image and the position of the virtual viewpoint and the view direction from the virtual viewpoint, and to cause a displaying unit to display the determined display target image in a displaying mode according to a degree of contribution of the determined display target image to generation of the virtual viewpoint image.

Abstract: Methods and apparatus provide, for each partial area into which a display area is divided, determining multiple pixel groups including pixels overlapping a two-dimensional area; allocating the pixels belonging to the multiple pixel groups to any one of multiple processing groups that are each capable of including pixels whose number is smaller than or equal to a predetermined parallel number; calculating in parallel each color of pixels belonging to the processing group on the basis of the color calculation information stored in the memory; and outputting image data on the basis of the calculated color.

Abstract: Briefly, in accordance with one or more embodiments, an apparatus comprises a processor to compute depth values for one or more 4×4 blocks of pixels using 16 source interpolators and 8 destination interpolators on an incoming fragment of pixel data if the destination is in min/max format, and a memory to store a depth test result performed on the one or more 4×4 blocks of pixels. Otherwise the processor is to compute depth values for one or more 8×4 blocks of pixels using 16 source interpolators and 16 destination interpolators if the destination is in plane format.

Abstract: An example method for determining three-dimensional coordinates of an object from a plurality of two-dimensional images may include: acquiring two-dimensional input frames via a camera, the camera being associated with one or more calibration parameters; isolating a contour of at least one object contained within each input frame; calculating coordinates of one or more visual rays corresponding to each contour in a direction specified by at least one of the calibration parameters; estimating a spatial tangent vector of each contour using finite differences; estimating a tangent space of the visual rays at each visual ray; calculating epipolar numbers based on basis vectors of the tangent space, the one or more calibration parameters, and the tangent vector; forming a line-based epipolar matrix using the epipolar numbers and line coordinates; and de-homogenizing the column space of the matrix into object points.

Abstract: A prediction system for determining a set of subregions can be used for rendering a virtual world of a computer graphics application. The subregions belong to streamable objects to be used for rendering the virtual world. The streamable objects each comprise a plurality of subregions. The prediction system comprises a plurality of predictor units arranged for receiving from a computer graphics application information on the virtual world and each arranged for obtaining a predicted set of subregions for rendering a virtual world using streamable objects. Each predicted set can be obtained by applying a different prediction scheme. A streaming manager is arranged for receiving the predicted sets of subregions, for deriving from the predicted sets a working set of subregions to be used for rendering and for outputting, based on the working set of subregions, steering instructions concerning the set of subregions to be actually used.

Abstract: An apparatus for supervising a vicinity of a vehicle includes: an image capturing unit that captures a plurality of images in which an object is simultaneously captured from different locations; a parallax calculation unit that performs a sub pixel estimation based on the plurality of images to calculate a parallax value; a parallax offset calculation unit that calculates a parallax offset value based on the parallax value under a condition where a decimal part S of the parallax value is within a predetermined range; and a parallax correction unit that corrects the parallax value using the parallax offset value.

Abstract: Systems, apparatuses and methods may provide for technology that selects an anti-aliasing mode for a vertex of a primitive based on a parameter associated with the vertex and generates a coverage mask based on the selected anti-aliasing mode. Additionally, one or more pixels corresponding to the vertex may be shaded based at least partly on the coverage mask, wherein the selected anti-aliasing mode varies across a plurality of vertices in the primitive.

Abstract: Visual observation of morphological features of a cell group or individual cells acquired in 3D image data is facilitated, thus improving observation accuracy. Provided is an image processing device that generates, on the basis of a plurality of 2D images acquired by a microscope at different focus positions on a cell clump, 3D images of respective cells constituting the cell clump, that processes the generated 3D images and analyzes feature amounts on the basis of at least one measurement parameter, that displays analysis results in a graph, that allows a user to select a region of interest on the displayed graph, and that generates, from the 3D images that correspond to the plurality of cells that are included in the selected region of interest, 2D display images each in a plane with reference to an axis that is determined on the basis of a shape feature of the corresponding cell and displays the 2D display images in a list.

Abstract: Methods and systems for use of a reference image to detect a road obstacle are described. A computing device configured to control a vehicle, may be configured to receive, from an image-capture device, an image of a road on which the vehicle is travelling. The computing device may be configured to compare the image to a reference image; and identify a difference between the image and the reference image. Further, the computing device may be configured to determine a level of confidence for identification of the difference. Based on the difference and the level of confidence, the computing device may be configured to modify a control strategy associated with a driving behavior of the vehicle; and control the vehicle based on the modified control strategy.

Abstract: A method for controlling a digital display device (105), such as a digital micro-mirror device, and a digital display apparatus (101, 106) are provided in which, in order to meet the latency requirements of the display, each frame of received image symbology data is divided into several subframes. A tag is assigned to an incoming drawing command, the tag having an initial value equal to the number of subframes in a frame. The drawing command is rendered on the first subframe and the tag is decremented by one. The drawing command is rendered again on subsequent subframes and the tag value is decremented by one each time the drawing is rendered. When the tag value reaches zero, the drawing command is discarded. Thus, a line may be rendered with lower latency compared with known systems which refresh on a frame-by-frame basis.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining a minimum visible change value for a particular animation comprising multiple frames, the minimum visible change value corresponding to a condition at which change to the particular animation is not visible; determining, based on the minimum visible change value, a termination threshold distance from an animation endpoint and a termination threshold velocity for the particular animation; for each frame of the particular animation, determining whether a current distance from the animation endpoint satisfies the termination threshold distance from the animation endpoint and a current velocity satisfies the termination threshold velocity; and in response to determining that the current distance from the animation endpoint satisfies the termination threshold distance from the animation endpoint and the current velocity satisfies the termination threshold velocity, initiating termination of the animatio

Abstract: A simulator is disclosed. A cockpit model comprising a plurality of cockpit model parts that collectively correspond to a simulated cockpit in a simulated vehicle is maintained. For each frame of a plurality of frames, a plurality of cockpit view frustums are determined, each cockpit view frustum corresponding to a different cockpit view of a plurality of cockpit views of the simulated cockpit. Shared cockpit scene information comprising a set of cockpit model parts that are within any of the plurality of cockpit views is generated based on the plurality of cockpit view frustums. A processing device submits to a graphics processing unit (GPU) the shared cockpit scene information and GPU instructions that direct the GPU to generate a plurality of cockpit view images that correspond to the plurality of cockpit views from the shared cockpit scene information. The GPU generates the plurality of cockpit view images.

Abstract: A three-dimensional (3D) depth imaging system is provided for use in commercial trailer loading applications. A 3D-depth camera may be configured and oriented to capture 3D image data of a vehicle storage area. A depth-detection application executing on one or more processors may determine, based on the 3D image data, at least a wall data region and a non-wall data region. Based on the determination of the wall data and the non-wall data region, the depth-detection application generates a wall indicator that indicates a wall is situated at a discrete depth within the vehicle storage area.

Abstract: Apparatus, method, and computer program code for producing composite image. A method comprises: obtaining (150) a first image (130) with first depth information; obtaining (152) a second image (132) with second depth information; detecting (154) regions of interest in the first image (130); segmenting (156) the regions of interest into individual layers; performing (158) image compensation for the individual layers according to the first depth information so that in image compensated individual layers a perspective and/or a viewpoint of the first image (130) is modified to be more similar with the second image (132); and rendering (160) the image compensated individual layers with the second image (132) utilizing the first depth information and the second depth information in order to produce a composite image (134).