Abstract: A computer-implemented method for adaptive mesh refinement includes generating a first mesh for a first layer of a stacked model representing a 3D integrated circuit, the first mesh including a first grid for the first layer, performing a simulation for the stacked model using the first mesh to obtain first results, calculating an interpolated value for a particular grid node according to the first results, the particular grid node corresponding to a node of the first grid in the grid hierarchy. The method further includes generating a second mesh for the layer of the stacked model, the second mesh including a second grid for the first layer, performing a simulation for the stacked model using the second mesh to obtain a simulated value of the particular grid node, comparing the interpolated and simulated value, and generating a refined mesh for the first layer including a refined grid.

Abstract: A method for minimizing latency of moving objects in an augmented reality (AR) display device is described. In one aspect, the method includes determining an initial pose of a visual tracking device, identifying an initial location of an object in an image that is generated by an optical sensor of the visual tracking device, the image corresponding to the initial pose of the visual tracking device. rendering virtual content based on the initial pose and the initial location of the object, retrieving an updated pose of the visual tracking device, tracking an updated location of the object in an updated image that corresponds to the updated pose, and applying a time warp transformation to the rendered virtual content based on the updated pose and the updated location of the object to generate transformed virtual content.

Abstract: The technologies disclosed herein relate to a system and method for transferring markings. The system can include an imaging device for imaging a stained slide and an unstained slide, a display for displaying one or more images of the stained slide and the unstained slide. In various embodiments, the system can include a mechanical stage, such as a scaffold, for positioning or orienting the stained slide with respect to the unstained slide. In various embodiments, the system can be coupled with a first application for aligning the images to enable digital marking of the unstained slide and a second application for digitally marking one or more features and transferring the digital markings into coordinates to be used for further processing, such as for dissection.

Abstract: In one implementation, a method of pipelined blending an image with virtual content is performed by a device including an image sensor, a display, one or more processors, and non-transitory memory. The method includes capturing, with the image sensor, a first portion of an image of a physical environment. The method includes warping the first portion of the image of the physical environment to generate a warped first portion. The method includes blending the warped first portion with a first portion of virtual content to generate a blended first portion. The method includes displaying, on the display, the blended first portion. The method includes capturing, with the image sensor, a second portion of the image of the physical environment. The method includes warping the second portion of the image of the physical environment to generate a warped second portion. The method includes blending the warped second portion with a second portion of the virtual content to generate a blended second portion.

Abstract: A method, non-transitory computer readable medium, apparatus, and system for image generation are described. An embodiment of the present disclosure includes obtaining an input image, an inpainting mask, and a plurality of content preservation values corresponding to different regions of the inpainting mask, and identifying a plurality of mask bands of the inpainting mask based on the plurality of content preservation values. An image generation model generates an output image based on the input image and the inpainting mask. The output image is generated in a plurality of phases. Each of the plurality of phases uses a corresponding mask band of the plurality of mask bands as an input.

Abstract: A system and method for navigation in complete darkness with thermal imaging and virtual-reality headset provide adjustable-base stereopsis and maintain long-range situational awareness. Such a system includes a multiple-aperture thermal imaging subsystem with non-collinear sensors with parallel optical axes and an image processing device, resulting in a significantly more accurate depth map than perceived with a normal human stereo acuity from a pair of raw thermal images. The stereo-video presented to the user is synthetic, allowing vantage point and stereo-base adjustment; it augments natural objects' texture with the generated one to allow a 3D perception of the negative obstacles and other horizontal features that do not provide stereo cues for the horizontal binocular vision.

Abstract: Embodiments of the present disclosure provide an image processing method and apparatus, and a device. The method includes: displaying a number M of first images in a first region, each first image corresponding to a number N of sub-images, the number N of sub-images being images formed by dividing the first image into N parts, M being an integer greater than or equal to 1, and N being an integer greater than 1; in response to a first operation instruction, determining a number K of sub-images from the number of M*N sub-images corresponding to the number M of first images, and displaying some or all of the K sub-images in a second region, K being an integer greater than or equal to 1; and updating a display mode of the number M of first images according to the K sub-images, and displaying a splicing number corresponding to each first image, the splicing number being a number of first images formed by splicing the K sub-images.

Abstract: Techniques for augmenting a view of a first user of a first mixed reality (MR) visualization device in an operating room are described. For example, an intraoperative guidance system is configured to determine a location for a second user to stand within the operating room. A second MR visualization device is configured to be worn by the second user. The second MR visualization device is further configured to present a MR visualization that indicates the location for the second user to stand within the operating room. The first MR visualization device is configured to present a MR visualization that contains a window that show images of a surgical site captured by a camera supported by the second user.

Abstract: A data augmentation method and system for generating enriched training images using diffusion models, hybrid concatenation, and fractal blending. An original image and at least one prompt are input to a diffusion model to generate a corresponding image. A hybrid image is formed by concatenating a portion of the original image with a remaining portion of the generated image, wherein concatenation is performed using a binary pixel-wise mask. The mask comprises pixels valued at zero or one, with at least one entire row or column set to zero. The concatenation includes multiplying pixels of the original image with the mask and multiplying pixels of the generated image with the complement of the mask. A fractal image is blended into the hybrid image using a blending factor to produce an augmented image.

Abstract: An improved interactive graphics tool including an algorithm and technique to efficiently and elegantly render smooth lines to build or develop interactive graphics is disclosed. The new algorithm is configured to render an anti-aliased coverage mask for any path, using a single GPU shader program and a single GPU draw call. The present invention is a solution to prior two-dimensional graphics, by providing an automated process to stroke the entire path with tessellation, by rendering to a floating point “coverage count” buffer to tessellate an antialiasing with triangles running orthogonally from the center.

Abstract: Methods and systems for training a model include training an encoder in an unsupervised fashion based on a backward latent flow between a reference frame and a driving frame taken from a same video. A diffusion model is trained that generates a video sequence responsive to an input image and a text condition, using the trained encoder to determine a latent flow sequence and occlusion map sequence of a labeled training video.

Abstract: A method and apparatus with image processing is provided. The processor-implemented method includes generating a warped image frame by warping a first reconstructed image frame of a first time point based on first change data corresponding to a change between first rendered image frame of the first time point and second rendered image frame of a second time point that is different from the first time point; generating, using a neural reconstruction model based on the second rendered image frame and the warped image frame, a confidence map representing a second reconstructed image frame of the second time point and confidence scores of pixels of the second reconstructed image frame; and generating a third rendered image frame of a third time point, different from the first and second time points, by ray tracing for each of plural pixels of the third rendered image frame based on the confidence map.

Abstract: Systems, methods, and other embodiments described herein relate to using octrees and trilinear interpretation to generate field-specific representations. In one embodiment, a method includes acquiring a latent vector describing an object. The method includes generating an octree from the latent vector according to a recursive network, the octree representing the object at a desired level-of-detail (LoD). The method includes extracting features from the octree at separate resolutions. The method includes providing a field as a representation of the object according to the features.

Abstract: An extended reality (XR) streaming method of streaming XR images between a plurality of XR application instances and an XR device is described. The XR streaming method comprises streaming, with a first XR application instance first XR images to the XR device, wherein the first XR images streamed by the first XR application instance are associated with a first XR application. Streaming, by means of a second XR application instance, second XR images to the XR device, wherein the second XR images streamed by the second XR application instance are associated with a second XR application. Blending, by means of the XR device, the first XR images received from the first XR application instance with the second XR images received from the second XR application instance to obtain blended XR images for display on the XR device.

Abstract: Embodiments relate to a method for generating an image comprising a graphical representation. The method includes determining a transformation relationship for a unit cell of a graphical representation of an original image. The transformation relationship is based on position information of grid vertices of the unit cell of the original image graphical representation and position information of grid vertices of a unit cell of a reference grid arrangement of the image to be generated. The method further includes determining position information of a one or more pixels of the unit cell of the original image graphical representation based on the transformation relationship. The method further includes applying data information sampled at the one or more pixels of the unit cell of the original image graphical representation to one or more pixels of the unit cell of the reference grid arrangement.

Abstract: One embodiment provides circuitry coupled with cache memory and a memory interface, the circuitry to compress compute data at multiple cache line granularity, and a processing resource coupled with the memory interface and the cache memory. The processing resource is configured to perform a general-purpose compute operation on compute data associated with multiple cache lines of the cache memory. The circuitry is configured to compress the compute data before a write of the compute data via the memory interface to the memory bus, in association with a read of the compute data associated with the multiple cache lines via the memory interface, decompress the compute data, and provide the decompressed compute data to the processing resource.

Abstract: An apparatus in an illustrative embodiment comprises at least one processing device that includes a processor coupled to a memory, with the at least one processing device being configured to obtain at least a portion of a uniform resource locator (URL) presented in a browser, to determine at least one of a domain and one or more cookies associated with the URL, to generate a file comprising information characterizing the at least one of the domain and the one or more cookies associated with the URL, to generate a multi-dimensional code based at least in part on the generated file, and to present the multi-dimensional code via the browser for scanning. The multi-dimensional code in some embodiments is presented for scanning by a mobile application of a mobile device of a user.

Abstract: An information presenting method, a presenting system, an electronic device, and a computer-readable storage medium are disclosed. The information presenting method includes: presenting data information in a data presenting panel layer; and presenting three-dimensional model information in a three-dimensional model presenting layer, the three-dimensional model presenting layer is different from the data presenting panel layer; the data presenting panel layer and the three-dimensional model presenting layer communicate with each other through a support layer, and the data information is associated with the three-dimensional model information. The information presenting method can allow a user to conveniently view a scene presented by the three-dimensional model and the data information corresponding to the scene, which reduces operational complexity for the user to view the scene and the data corresponding to the scene.

Abstract: A method and a decompression unit are provided for decompressing compressed data to determine a sub-primitive presence indication for use in intersection testing in a rendering system. A block of compressed data for a block of sub-primitive presence indications is received. An indication of a sample position within the block of sub-primitive presence indications for which a presence indication is to be determined is received. Data defining an ordered set of patches which represents the presence indications in the block of sub-primitive presence indications is read from the block of compressed data. The data defining each of the patches defines a presence state of the patch and a position of the patch within the block of sub-primitive presence indications. At least two of the patches in the set of patches partially overlap with each other. For one or more of the patches, it is determined whether the sample position is within that patch.

Abstract: A system for real-time animation interactive editing is provided. The system for real-time animation interactive editing includes a physics simulation platform and an animation processing device. The animation processing device includes an animation editing circuit and a comparison processing circuit. The animation editing circuit is configured to obtain a motion animation associated with a robot and provide the motion animation to the physics simulation platform, such that the physics simulation platform performs a simulation processing based on the motion animation to generate a simulation result. The comparison processing circuit is configured to real-time obtain the simulation result generated by the physics simulation platform, and compare the simulation result with the motion animation to generate a comparison result.