Abstract: A method includes obtaining, by a first agent engine that generates actions for a first agent, a first objective of the first agent. In some implementations, the method includes generating, by the first agent engine, a first influence for a second agent engine that generates actions for a computer-generated reality (CGR) representation of a second agent. In some implementations, the first influence is based on the first objective of the first agent. In some implementations, the method includes triggering the CGR representation of the second agent to perform a set of one or more actions that advances the first objective of the first agent. In some implementations, the second agent engine generates the set of one or more actions based on the first influence generated by the first agent engine.

Abstract: The present invention provides a cable network planning method comprising: modelling the prespecified topology as a Steiner tree including a plurality of terminal nodes representing a plurality of cable landing stations (CLSs) to be installed respectively in a plurality of destination regions connected by the cable network, a plurality of Steiner nodes presenting a plurality of branching units (BUs) to be installed in the cable network, and a plurality of edges connecting the terminal nodes and Steiner nodes; constructing a directed acyclic graph (DAG); finding a Steiner minimal tree (SMT) by applying a DAG-Least-Cost-System algorithm; returning coordinates of Steiner nodes, terminal nodes of the SMT as locations of the BUs and the CLSs. The provided method enables inclusion of costs of the Steiner nodes by taking account of Steiner nodes with degree in excess of three such that more flexible BU branching structures and CLS locations alternatives can be considered.

Abstract: An application server associated with an online marketplace may receive a set of images of an item, spatial information associated with each image of the set of images indicating a relative spatial location to the item for each image, and viewing direction information indicating a viewing direction relative to the item for each image. The application server may then generate a neural radiance field model of the item in a three dimensional space based on the set of images, the spatial information, and the viewing direction information, and may generate a set of spherical harmonics for the neural radiance field model based on predicting one or more spherical harmonic coefficients using the set of images, the spatial information, and the viewing direction information. The application server may then output a three dimensional model of the item generated based on the set of spherical harmonics.

Abstract: Techniques of introducing virtual objects into a physical environment of AR system include displacing vertices of a mesh representing the physical environment based on a live depth map. For example, an AR system generates a mesh template, i.e., an initial mesh with vertices that represents a physical environment and a depth map that indicates a geometry of real objects within the physical environment. The AR system is configured to represent the real objects in the physical environment by displacing the vertices of the mesh based on depth values of the depth map and parameter values of a pinhole camera model. The depth values may be taken from the perspective of an illumination source in the physical environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for monitoring extended reality spaces. One of the methods includes maintaining, for an extended reality environment generated by a first device operated by a person, data defining a three-dimensional space at a property; accessing sensor data generated by one or more sensors physically located at the property; predicting, using the sensor data, that an object will likely interfere with the three-dimensional space at the property; and in response to predicting that the object will likely interfere with the three-dimensional space at the property, providing a notification to a second device.

Abstract: This application discloses a for displaying a two-dimensional figure of a virtual object performed by a computer device. The method includes: rendering a two-dimensional image of a virtual object based on a corresponding three-dimensional figure model according to a plurality of preset parameters; displaying a target interface comprising the two-dimensional image of the virtual object; and displaying an updated two-dimensional image of the virtual object when an update condition is met, wherein the updated two-dimensional image corresponds to the three-dimensional figure model of the virtual object.

Abstract: A periphery monitoring device calculates an expected passage range indicating a range of a locus of a machine body when a lower travelling body travels in an imaging direction of a camera, based on a slewing angle of an upper slewing body and an attitude of an attachment, and superimposes a range image indicating the calculated expected passage range on an image captured by the camera to display the superimposed image on the display.

Abstract: Disclosed are an interfacing method and an apparatus for three-dimensional (3D) sketch. According to an example embodiment, the interfacing method for sketching in a virtual space of three dimensions includes determining a surface including an area in which a first user input is received in the virtual space to be a region of interest, controlling a position of the region of interest in the virtual space based on a second user input on the region of interest, and generating at least one sketch line belonging to the region of interest based on a third user input.

Abstract: An example method comprises simulating an environment including at least one simulated object, a simulated ray source, and a simulated receiver, simulating a plurality of rays emitting from the simulated ray source, tracking each ray in the environment, detecting changes for at least one ray that interacts with the at least one simulated object, the changes for the at least one ray including a reflection from the at least one object, tracking the reflection of the at least part of the ray from the at least one object in the environment, determining measurements for any of the plurality of rays that interact with the simulated receiver in the simulation, the at least part of the ray being received by the receiver, the measurements including intensity for any of the plurality of rays that interact with the receiver, and generating synthetic point cloud data based on the measurements.

Abstract: Apparatuses, systems, and techniques for buffer identification of an application for post-processing. The apparatuses, systems, and techniques includes generating a buffer statistic data structure for a buffer of a plurality of buffers associated with a frame of an application; updating the buffer statistic data structure with metadata of the draw call responsive to detecting a draw call to the buffer; and determining, based on the buffer statistic data structure, a score reflecting a likelihood of the buffer being associated with a specified buffer type.

Abstract: System and method are provided for scaling a 3-D representation of a building structure. The method includes obtaining world map data including a first track of real-world poses for a plurality of images. The plurality of images comprises non-camera anchors. The method also includes detecting a discrepancy in at least one real-world pose of the first track. The method also includes in response to detecting a discrepancy, generating a new track of real-world poses. The method also includes calculating a scaling factor for a 3-D representation of the building structure based on sampling across a plurality of tracks. The plurality of tracks comprises at least the first track and the new track.

Abstract: Embodiments of the present disclosure provide systems, methods, and computer storage media for generating editable synthesized views of scenes by inputting image rays into neural networks using neural basis decomposition. In embodiments, a set of input images of a scene depicting at least one object are collected and used to generate a plurality of rays of the scene. The rays each correspond to three-dimensional coordinates and viewing angles taken from the images. A volume density of the scene is determined by inputting the three-dimensional coordinates from the neural radiance fields into a first neural network to generate a 3D geometric representation of the object. An appearance decomposition is produced by inputting the three-dimensional coordinates and the viewing angles of the rays into a second neural network.

Abstract: A graphics processing system for generating a rendering output includes geometry processing logic having first transformation logic configured to transform a plurality of untransformed primitives into a plurality of transformed primitives, the first transformation logic configured to implement one or more expansion transformation stages which generate one or more sub-primitives; a primitive block generator configured to divide the plurality of transformed primitives into a plurality of groups; and generate an untransformed primitive block for each group comprising (i) information identifying the untransformed primitives related to the transformed primitives in the group; and (ii) an expansion transformation stage mask for at least one or more expansion transformation stages that indicates the sub-primitives generated for the untransformed primitives in that untransformed primitive block used in generating the rendering output.

Abstract: Embodiments include receiving image data comprising a representation of teeth, wherein the image data comprises a set of pixel locations for the teeth and depth values associated with the pixel locations in the set of pixel locations. The method further includes generating new image based on applying one or more functions to the image data, wherein the one or more functions adjust one or more color channels of the set of pixel locations based at least in part on the depth values.

Abstract: Three-dimensional (3D) modeling systems and methods are described for automatically generating photorealistic, virtual 3D package and product models from 3D and two-dimensional (2D) imaging assets. The 3D modeling systems and methods include loading, into a memory with one or more processors, computer-aided design (CAD) component(s) and assembling, with an automatic imaging asset assembly script, the CAD component(s) to create a parametric-based CAD model. A polygonal model of a real-world product or product package is generated based on the parametric-based CAD model. Digital surface finish artifact(s) of a virtual material library, as selected from the 2D imaging assets, are applied to the polygonal model. A virtual 3D model is generated based on the polygonal model and a UV coordinate mapping corresponding to a virtual product label, and rendered, via a graphical display, as a photorealistic image representing the real-world product or product package.

Abstract: A computer-implemented method for transforming a neural radiance field model is described. A plurality of inputs are provided to a neural radiance field (NeRF) model that represents a 3-dimensional space having a subject, wherein each input of the plurality of inputs includes a location and a view direction and corresponds to respective colors of voxels that represent the 3-dimensional space. A spectral analysis is performed on a plurality of outputs of the NeRF model based on the plurality of inputs, wherein the plurality of outputs include the respective colors of the voxels. Frequency components of the spectral analysis that represent colors for at least some of the voxels are extracted. A sparse volume data structure that represents the 3-dimensional space and the respective colors for the at least some of the voxels is generated.

Abstract: A smart render design tool includes: (a) a designer side plug-in enabling a designer to generate credentials for a client and associate the credentials with a model for the client, add camera view(s) to the model, select one or more surfaces in the camera view(s) to add in the model, specify one or more materials for each surface of the one or more surfaces of the model, and publish the model including the specified materials for the one or more surfaces of the model; and (b) a client side portal associated with the credentials and the model enabling the client to access the published model using the generated credentials, select desired materials from among the materials specified by the designer for each surface of the published model, and save the desired materials selections of the client for review by the designer using a synchronization function of the designer side plug-in.

Abstract: A mixed reality space sharing system is provided with which 3D information regarding a target real space can be shared between a plurality of MR terminals while keeping the information updated, without spending a long processing time. A shared information management server includes an information management unit for creating a room by associating, with each other, 3D information and anchor information that are transmitted from a first terminal, which is at least one of a plurality of mixed reality terminals, and managing the 3D information, and a sharing unit for transmitting the 3D information and the anchor information to a second terminal different from the first terminal. The second terminal downloads the 3D information and the anchor information transmitted from the shared information management server and creates a mixed reality space using the downloaded information.

Abstract: Systems and methods are provided to create training data, validate, deploy and test artificial intelligence (AI) systems in a virtual development environment, incorporating virtual spaces, objects, machinery, devices, subsystems, and actual human action and behavior.

Abstract: A method, server, system, and computer program product creates a three-dimensional (3D) virtual certificate of authenticity (COA) that is a multimedia container having a media file that provides for an experiential presentation in the 3D COA itself. The multimedia container with media file lends credibility to the authenticity of the 3D COA. The ownership of the 3D COA can be stored in a blockchain as a non-fungible token, and easily transferred from one claimant of the 3D COA to another.

Abstract: The present disclosure generally relates to displaying visual effects in image data. In some examples, visual effects include an avatar displayed on a user's face. In some examples, visual effects include stickers applied to image data. In some examples, visual effects include screen effects. In some examples, visual effects are modified based on depth data in the image data.

Abstract: The space recognition system includes: an information terminal of a user having a function of displaying an image on a display surface and having a terminal coordinate system WA; and a label which is provided to correspond to a space and in which information for identifying the space is described. When recognizing the space, the information terminal specifies space data in which the space and the label are described in a space coordinate system W1 by using the information read from recognition of the label, measures relations in a position and a direction between the information terminal and the label by using the space data, and adapts the terminal coordinate system WA to the space coordinate system W1, based on data representing the measured relations.

Abstract: A method for comparing two or more three-dimensional (3D) object model by evaluating at least one 3D triangle from each received triangular mesh data. For each reference triangle, the method includes identifying one or more adjacent triangles using conditions for congruence of triangles and performing neighbor facet edge hashing to produce an object hash value for each of the at least one 3D triangle. The method includes comparing the object hash value to one or more reference hash values assigned respectively to one or more 3D object models. The method includes determining whether a match exists between one or more 3D object models and the reference object based upon an amount of matching of obtained hash values. In one or more embodiments, a method compares 3D triangle objects, such as a prior scan of the same object, to determine deviations over time or the subtraction or addition of sub-parts.

Abstract: Some examples of the disclosure are directed to systems and methods for presenting content in a three-dimensional environment by one or more electronic devices in a multi-user communication session. In some examples, a first electronic device and a second electronic device are communicatively linked in a multi-user communication session, wherein the first electronic device and the second electronic device are configured to display a three-dimensional environment, respectively. In some examples, the first electronic device and the second electronic device are grouped in a first spatial group within the multi-user communication session. In some examples, if the second electronic device determines that the first electronic device changes states (and/or vice versa), the user of the first electronic device and the user of the second electronic device are no longer grouped into the same spatial group within the multi-user communication session.

Abstract: A three-dimensional (3D) graphics system automatically defines or accurately adjusts normals for primitives of a 3D model. The system receives the 3D model primitives, selects a particular primitive at a specific position relative to other primitives of the 3D model, and defines a normal with a first direction for the particular primitive based on an association of the normal with the first direction to the specific position. The system then selects a set of primitives with positions next to the particular primitives, and defines a normal for each primitive of the set of primitives with a second direction that is perpendicular to a surface spanned between positions of the particular primitive and each primitive of the set of primitives.

Abstract: Described herein is a process and system for constructing three-dimensional (3D) representations of roof structures. The system can create representations of roof structures of arbitrary complexity and can create representations of dependent roof structures such as dormers. The system can create representations of roof structures that conventional methods cannot create, such as roofs with edges that are not coplanar, roofs with faces that do not connect to exterior edges, roofs composed of sub-structures, or roofs with dependent structures such as dormers.

Abstract: A computer-generated virtual object manipulator having one or more affordances for manipulating a computer-generated virtual object is disclosed. Selection of a virtual object can cause an object manipulator to be displayed over the virtual object. The object manipulator can include a cone-shaped single-axis translation affordance for each of one or more object axes, a disc-shaped single-axis scale affordance for each of the one or more object axes, an arc-shaped rotation affordance for rotation about each of the one or more object axes, and a center of object affordance for free space movement of the virtual object. The object manipulator can also include a slice-shaped two-axis translation affordance that can be displayed after hovering over an area in a particular plane.

Abstract: A method for determining a travertine deposit by: receiving a geological gridded model comprising a plurality of cells; receiving a source cell or a group of source cells of the geological gridded model corresponding to a source; determining a trajectory of a particle introduced at the source based on stochastic movements; and updating a travertine deposit in cells located on the trajectory of the particle.

Abstract: A method for enhanced forward rendering is disclosed which includes a depth pre-pass, light culling and a final shading. The depth pre-pass minimizes the cost of final shading by avoiding high pixel overdraw. The light culling stage calculates a list of light indices overlapping a pixel. The light indices are calculated on a per-tile basis, where the screen has been split into units of tiles. The final shading evaluates materials using information stored for each light. The forward rendering method may be executed on a processor, such as a single graphics processing unit (GPU) for example.

Abstract: The analysis apparatus includes a calculation unit configured to calculate a transformation parameter used to transform a reference model indicating a three-dimensional shape of a target object into a three-dimensional shape indicated by three-dimensional sensing data indicating a result of sensing a target object after an elapse of a predetermined period of time since the reference model is generated; an update unit configured to update the reference model using the transformation parameter and three-dimensional sensing data; and a communication unit configured to transmit difference data between vertices of a reference model after the update and vertices of a reference model before the update, difference data between a representative point of the reference model after the update having the transformation parameter and a representative point of the reference model after the update, and a transformation parameter to a terminal device that shares a reference model.

Abstract: Detecting a movable object in a location includes providing a first 3D representation of at least part of a surface; providing a second 3D representation of at least part of the surface; determining for the first 3D representation a first excluded volume in space where no surface can be present; determining for the second 3D representation a second excluded volume in space where no surface can be present; if a portion of the surface in the first 3D representation is located in space in the second excluded volume, the portion of the surface in the first 3D representation is disregarded in the generation of the virtual 3D model, and/or if a portion of the surface in the second 3D representation is located in space in the first excluded volume, the portion of the surface in the second 3D representation is disregarded in the generation of the virtual 3D model.

Abstract: A method and arrangement for dynamically updating and expanding a digital building model (BIM, digital twin) with respect to furniture information for rooms, wherein the recording of the seating configuration of a room takes place by means of a correspondingly configured recording device (e.g. mapping apparatus, NavVis apparatus, smartphone camera); wherein a mapping of the seating configuration of the room into a digital building model (BIM) takes place, wherein the recording of the seating configuration of the room and the mapping of the seating configuration of the room into the digital building model (BIM) takes place in a time-controlled or event-controlled manner.

Abstract: A method and apparatus for transforming an input model according to an example embodiment are disclosed. The method includes receiving an input model including a first mesh with a first topology, generating a template model including a second mesh with a second topology, aligning the template model with the input model, generating correlation information between the second mesh of the aligned template model and the first mesh of the input model, generating, based on a skeleton of the aligned template model, a skeleton of the input model, generating, based on the correlation information, first skinning information indicating a connection relation between the skeleton of the input model and the first mesh, and transforming, based on at least one of the correlation information and the first skinning information, the input model.

Abstract: Aspects presented herein relate to methods and devices for graphics processing including an apparatus, e.g., a GPU or CPU. The apparatus may allocate each of a plurality of primitives in a scene into one of a plurality of bounding boxes, each of the plurality of bounding boxes corresponding to a plurality of nodes including internal nodes and leaf nodes. The apparatus may also identify whether each of the plurality of nodes is one of the internal nodes or one of the leaf nodes. Further, the apparatus may estimate a compressibility of each of the plurality of nodes if the node is one of the leaf nodes, the compressibility of the node corresponding to whether the node is compressible. The apparatus may also compress data corresponding to each of the plurality of nodes if the node is estimated to be compressible.

Abstract: Disclosed are a robot arm control method, a skin surface treatment apparatus, and a computer-readable memory medium, which relate to the field of mechanical control. the robot arm control method includes steps of: demarcating a to-be-treated surface of an object treated by a robot arm into at least two areas of interest; obtaining, by a three-dimensional scanning device, a three-dimensional point cloud corresponding to each area of interest; optimizing respective three-dimensional point clouds; merging the respective three-dimensional point clouds to obtain an executive point cloud; creating a motion path for the robot arm based on the executive point cloud; and performing, by the robot arm, a treatment to the surface of the object based on the motion path. Compared with conventional technologies, the disclosure has a better cost-effectiveness, an enhanced treatment efficiency, and an improved apparatus safety.

Abstract: Examples disclosed herein may involve a computing system that is operable to (i) generate first structure data from one or more first image data, wherein the first structure data comprises one or more visible features captured in the one or more first image data, (ii) generate further structure data from one or more further image data, wherein the further structure data comprises one or more visible features captured in the one or more further image data, (iii) determine pose constraints for the further structure data based on common visible features, (iv) determine a transformation of the further structure data relative to the first structure data using the determined pose constraints, and (v) generate combined structure data using the determined transformation to fuse the further structure data and the first structure data.

Abstract: A model generation system generates three-dimensional (3D) models for objects based on two-dimensional (2D) images of the objects. The model generation system may receive object images and generate a 3D object model for the object based on the object image. The model generation system may generate an object skeleton for the object based on the object image. The model generation system may use the object skeleton to generate pixel partitions representing parallel cross sections of the object. The model generation system may apply a machine-learning model (e.g., a neural network) to the object image to determine parameters for a shape that would best represent each parallel cross section and then generate the 3D object model for the object based on the shapes of each cross section, the object image, and the object skeleton.

Abstract: Systems are provided for generating data representing electromagnetic states of a heart for medical, scientific, research, and/or engineering purposes. The systems generate the data based on source configurations such as dimensions of, and scar or fibrosis or pro-arrhythmic substrate location within, a heart and a computational model of the electromagnetic output of the heart. The systems may dynamically generate the source configurations to provide representative source configurations that may be found in a population. For each source configuration of the electromagnetic source, the systems run a simulation of the functioning of the heart to generate modeled electromagnetic output (e.g., an electromagnetic mesh for each simulation step with a voltage at each point of the electromagnetic mesh) for that source configuration.

Abstract: An information processing apparatus includes a model-space storage unit that stores a 3D (three-dimensional) model of a predetermined object present in a real space, an object-information acquisition unit that acquires an image of the object taken by a camera of an augmented-reality display apparatus, a relation specifying unit that specifies a correspondence relation between a model coordinate system and a real-space coordinate system based on a result of a comparison between the image and the 3D model, a transformation unit that transforms coordinates in the model coordinate system for specifying a position at which a predetermined image is displayed into coordinates in the real-space coordinate system by using the correspondence relation, and a coordinate notification unit that notifies the augmented-reality display apparatus of the coordinates transformed by the transformation means.

Abstract: Techniques for meshing a plurality of objects include determining, for at least a portion of the objects, a respective priority level. A mesh is then generated for each object. Thereafter, at least a portion of the meshes are sequentially imprinted to each other such that conflicts arising between meshes are resolved in favor of an object having a higher priority level. Related apparatus, systems, techniques and articles are also described.

Abstract: The disclosure notably relates to a three-dimensional (3D) model. The data structure includes one delegated data object. The one delegate data object includes input parameters specific to a type of the delegated data object, and at least one operator specific to the type of the delegated data object for generating an output topology. The data structure also includes an output topology generated by the operator.

Abstract: A method with three-dimensional (3D) modeling of a wearer of a wearable device includes generating a feature map for each of a plurality of images of the wearer obtained from a plurality of imaging devices provided in the wearable device, obtaining joint keypoint information corresponding to joint positions of the wearer and initial shape coefficient information associated with a shape of the wearer based on the feature map for each of the images, determining a target 3D joint angle for 3D modeling of the wearer based on the joint keypoint information and the initial shape coefficient information, determining target shape coefficient information for 3D modeling of the wearer based on the joint keypoint information and the initial shape coefficient information, and obtaining a 3D mesh of the wearer based on the target 3D joint angle and the target shape coefficient information.

Abstract: The present disclosure is directed to a software tool that engages in a pattern matching technique. In one implementation, the software tool retrieves a two-dimensional drawing and identifies walls as lines, rotates the drawing until a threshold number of lines are aligned with either the X or Y axes, discards lines that are not aligned with either the X or Y axis, identifies intersection points, identifies a subset of intersection points that have a maxima or minima coordinate, constructs a data library indicative of the relative positions of the points in the identified subset; and compares the constructed data libraries for the two-dimensional drawing to data libraries constructed for another two-dimensional drawing.

Abstract: A computerized method comprising acquiring an image of a physical environment comprising one or more physical entities; generating a virtual view based on the acquired image, the virtual view being a 3D representation of the physical environment and comprising 3D data corresponding to the one or more physical entities of the physical environment; displaying the virtual view overlaid on the acquired image of the physical environment; obtaining bounding volumes for a plurality of 3D object models; merging said bounding volumes for the plurality of 3D object models into a virtual bounding volume, said merging occurring with respect to a particular 3D point within each one of the bounding volumes such that the particular 3D points coincide in the virtual bounding volume; and displaying the virtual bounding volume in the virtual view.

Abstract: Systems, methods, and other embodiments associated with generating aggregate data geospatial grid cells for encoding in vector tiles are described. In one embodiment, a method includes identifying a subset of finest-resolution geospatial grid cells contained by a vector tile in a set of finest-resolution geospatial grid cells and their associated aggregate data values; selecting a cell resolution level based on a zoom level of the vector tile; generating a new geospatial grid cell at the cell resolution level based on cell IDs of the subset of finest-resolution cells; generating a total aggregate data value for the new cell based on associated aggregate data values of the subset of finest-resolution cells; encoding the new cell and total aggregate data value in the vector tile; and transmitting the encoded vector tile to a client to cause the vector tile and the new cell to be displayed.

Abstract: Aspects and implementations of the present disclosure address shortcomings of the existing technology by enabling efficient object identification and tracking in autonomous vehicle (AV) applications by using velocity data-assisted mapping of first set of points obtained for a first sensing data frame by a sensing system of the AV to a second set of points obtained for a second sensing data frame by the sensing system of the AV, the first set of points and the second set of points corresponding to an object in an environment of the AV, and causing a driving path of the AV to be determined in view of the performed mapping.

Abstract: Provided is a system for providing removals simulation using VR and AR and brokering real estate therethrough, and the system includes: a background providing unit which extracts background information inside a real estate object provided by a real estate provider and presents the background information to the real estate customer; and an AR providing unit which overlaps props information of a real estate customer on the background information of the real estate object so as to be arbitrarily arranged by the real estate customer, wherein the real estate customer can simulate by overlapping props information on the background information, when the simulation is determined, the determined information is transmitted to a number of moving service servers, and thus provides an advantage in that a number of moving centers can propose moving costs to the real estate customer in a reverse auction manner based on the props information.

Abstract: The device (1) for estimating the distance between an observer (2) and a target (4) using at least one image generated by a digital image generator (6) from the position (P1) of the observer (2) comprises a detection and identification unit configured to detect and identify a target (4) in the image and define an imaged representation of the target (4), and a distance estimation unit configured to perform, on the image, multiple different projections of a three-dimensional model of the target (4) to obtain projected representations of the target (4) and to select the projected representation most similar to the imaged representation, the distance associated with the selected projected representation representing the estimated distance (D) between the position of the observer (2) and the target (4).

Abstract: According to the present invention, techniques, including a method, and system, for creating a tangible object having customized features and digitizing the object for manipulation and use by a child user are provided. In particular, the invention provides a method for assembling customized features onto a tangible object and using artificial intelligence techniques for digitizing the object onto a computing device for manipulation and use by a child user.

Abstract: An object is to provide a model generation apparatus capable of generating a model for implementing a more precise simulation. Firstly, an object to be reconstructed on a 3D model is extracted from 3D image information, and an object model having a highest shape conformity degree with the object is acquired from among a plurality of object models available on the 3D model, and is associated with size information and disposed-place information of the object. Next, for each of acquired object models, the extracted object model is edited so as to conform with the size information of the object. Then, the edited object model is disposed on the 3D model so that the object model satisfies a physical constraint on the 3D model and conforms with the disposed-place information.