Abstract: A picture prediction method includes receiving a bitstream, parsing the bitstream to obtain a prediction mode of a current block, when the prediction mode of the current block is a combined intra and inter prediction mode, selecting an execution manner of a triangular prediction unit mode according to a preset policy, determining motion information of the current block according to the execution manner of the triangular prediction unit mode, performing a motion compensation process based on the motion information, to obtain an inter prediction sample, obtaining an intra prediction sample according to the prediction mode of the current block, and combining the inter prediction sample and the intra prediction sample to obtain a prediction picture of the current block.

Abstract: A three-dimensional data encoding method includes: generating a bitstream by encoding subspaces included in a current space in which three-dimensional points are included. The bitstream includes encoded data respectively corresponding to the subspaces. In the generating of the bitstream, a list of information about the subspaces is stored in first control information included in the bitstream. The subspaces are respectively associated with identifiers assigned to the subspaces, and the first control information is common to the encoded data. Each of the identifiers assigned to the subspaces respectively corresponding to the encoded data is stored in a header of a corresponding one of the encoded data.

Abstract: A system for and a method of generating an ordered list of instructions comprising a list of pixel coordinates which are vertices of triangles in a strip of a reference input image in a source coordinate system such that transformation of the vertices to a corresponding output image in a destination coordinate system causes the triangles to be mapped to a block of image data which maps to a block of line memory (or “texture cache”). The method comprises dividing the reference output image into a plurality of tiled sections in the destination coordinate system. The method comprises, for each section, defining first and second boundaries of an array of strips of pixels in the section by dividing the section into blocks of line memory.

Abstract: Provided is an image processing device including a matching unit that performs matching processing between a predetermined pattern on a surface of a 3D model of a biological tissue including an operating site generated on the basis of a preoperative diagnosis image and a predetermined pattern on a surface of the biological tissue included in a captured image during surgery, a shift amount estimation unit that estimates an amount of deformation from a preoperative state of the biological tissue on the basis of a result of the matching processing and information regarding a three-dimensional position of a photographing region which is a region photographed during surgery on the surface of the biological tissue, and a 3D model update unit that updates the 3D model generated before surgery on the basis of the estimated amount of deformation of the biological tissue.

Abstract: A method of detecting a target includes generating an image pyramid based on an image on which a detection is to be performed; classifying candidate areas in the image pyramid using a cascade neural network; and determining a target area corresponding to a target included in the image based on the plurality of candidate areas, wherein the cascade neural network includes a plurality of neural networks, and at least one neural network among the neural networks includes parallel sub-neural networks.

Abstract: Systems and methods are provided for contouring a set of medical images. Deformation field data is generated between a source image and a target image of the set of medical images. The deformation field data relates structures in the source image to corresponding structures in the target image and is generated in accordance with a deformable registration algorithm. The deformation field data is utilized to generate target contour data associated with the target image from source contour data, associated with the source image, that identifies one or more objects within the source image.

Abstract: First, a displacement field (first displacement field) for deforming a first image so as to associate the first image with a second image is calculated based on information on an input corresponding point group. Then, upon a corresponding point candidate pair being input, a displacement field (second displacement field) for deforming the first image so as to associate the first image with the second image is calculated with the corresponding point candidate pair taken into consideration as well. Thereafter, a matching degree is calculated based on a difference between the two displacement fields, and a determination result indicating a match or a mismatch is displayed on a display unit.

Abstract: A face detection apparatus detecting a face from an image which is captured by an imaging unit and includes the face, includes: a position detection unit that detects a position of a face part of the face from the image; an initial state determination unit that determines a model initial state on the basis of the position of the face part; and a model fitting unit that generates a model of the face on the basis of the image by using the model initial state.

Abstract: The invention relates to a method for generating a three-dimensional facial model the shape of which can changed on the basis of a plurality of images of faces of persons, including the steps that involve: generating a facial template; acquiring shapes from examples of faces of persons; repeatedly changing the shape of the template for each example of a face of a person, so that the shape of the changed template corresponds to the shape of the face example, and determining the change in shape between the initial template and the changed template; and generating the facial model as a linear combination of the shape of the template and the changes in shape between the initial template and the changed template, for each example of a face of a person. The invention also relates to a method for processing an image of a face of a person such as to generate a three-dimensional image of the face of the person from of said deformable model.

Abstract: A transform apparatus applied in an image processing system with an image capture module is disclosed. The transform apparatus comprises a geometry information detector, a parameter setup unit, a primitive assembly unit and a geometry processing circuit. The geometry information detector measures geometry information of the image capture module. The parameter setup unit calculates geometry parameters and determines whether to assert an enable signal according to the geometry information. The primitive assembly unit receives an original vertex list and the enable signal to generate a vertex/ID flow. The geometry processing circuit receives the geometry parameters and performs geometry transform operations over the vertex/ID flow in response to whether the first enable signal is asserted to generate a modified vertex list. The geometry information comprises at least one of a displacement and rotation angles of the image capture module.

Abstract: Hybrid image projection systems and methods can superimpose image components of an input image. An input image can be divided into smaller regions and at least one parameter of each region can be determined. The input image can be decomposed based on the parameter of each region into multiple, less correlated, orthogonal or quasi-orthogonal image components. Each projector can display respective image components so that the images projected may be optically superimposed on a screen. The superposition of orthogonal or quasi-orthogonal image components can result in superposition of images in an existing multi-projector image systems being more insensitive to inter-projector image misalignment. Superimposing orthogonal or quasi-orthogonal images can be used to avoid visible image degradation, and provide more robust image quality in a multiple projector system implementation.

Abstract: There is disclosed a device for imaging a body. In one arrangement, the device comprises a controller, storage storing electronic program instructions for controlling the controller, a display for displaying a user interface, and an input means. In one form, the controller is operable, under control of the electronic program instructions, to receive input via the input means, where the input comprises a first representation of the body, to process the first representation, to generate a second representation of the body on the basis of processing of the first representation, and to display the generated second representation via the display.

Abstract: An imaging system for tracking brain deformation, a method for tracking brain deformation, a method of operating a device for tracking brain deformation are disclosed. A first 3D representation (112) of a cerebrovascular vessel structure of a region of interest of an object is provided (110), and (114) a second 3D representation (116) of the cerebrovascular vessel structure are used to determine brain deformation. At least a part of the first 3D representation is elastically three-dimensionally registered (118) with at least a part of the second 3D representation. A deformation field (122) of the cerebrovascular vessel structure is determined (120) based on the elastic registration. The determined vessel deformation is applied (124) to a brain structure representation to determine a deformation (126) of the cerebral structure.

Abstract: Adeformation vector field (DVF) (22)is computed that relatively spatially registers a first image (16)and a second image (14). A contour (26)delineating a structure in the first image is adapted using the DVF to generate an initial contour (52)for the structure in the second image. A final contour (56)is received for the structure in the second image. The DVF is corrected based on the initial and final contours for the structure in the second image to generate a corrected DVF (32). The correction may comprise computing an adjustment DVF (62)relating the initial and final contours and combining the DVF and the adjustment DVF to generate the corrected DVF. The final contour may be received by displaying the second image overlaid with the initial contour, and receiving user adjustments of the overlaid contour with the overlaid contour updated for each received user adjustment.

Abstract: Systems and methods are described for animating 3D characters using synthetic motion data generated by generative models in response to a high level description of a desired sequence of motion provided by an animator. An animation system is accessible via a server system that utilizes the ability of generative models to generate synthetic motion data across a continuum to enable multiple animators to effectively reuse the same set of previously recorded motion capture data to produce a wide variety of desired animation sequences. An animator can upload a custom model of a 3D character and the synthetic motion data generated by the generative model is retargeted to animate the custom 3D character.

Abstract: In a pattern identification device performing pattern identification of data which has been input by hierarchically extracting features, a primary feature is extracted and distribution of at least one feature extraction result extracted is analyzed, a secondary feature is extracted according to this analysis result. Thus, it is possible to perform pattern identification robustly against fluctuations of the input pattern at a reduced processing cost while reducing the probability of occurrence of incorrect identification.