Abstract: An air-blowing apparatus includes a main body and a fan. In the main body a blow-out region is formed. The fan is provided in the main body and sends air toward the blow-out region. The air-blowing apparatus blows out air from the blow-out region such that a ratio (Vmax/Vmin) of a maximum value Vmax of wind velocity to a minimum value Vmin of the wind velocity is 1 or more and 10 or less in a target virtual plane. The target virtual plane is a virtual plane that faces the blow-out region. As a result, comfort of a person exposed to the wind sent from the air-blowing apparatus is improved.

Abstract: Methods and Systems for generating a centerline for an object in an image and computer readable medium are provided. The method includes receiving an image containing the object. The method also includes generating the centerline of the object, by a processor, using a reinforcement learning network configured to predict movement of a virtual agent that traces the centerline in the image. The reinforcement learning network is further configured to perform at least one auxiliary task that detects a bifurcation in a trajectory of the object. The reinforcement learning network is trained by maximizing a cumulative reward and minimizing an auxiliary loss of the at least one auxiliary task. Additionally, the method includes displaying the centerline of the object.

Abstract: One embodiment of the invention disclosed herein provides techniques for voxelizing a mesh representation associated with a three-dimensional model to generate a volumetric model. A model filling engine associated with a voxelization system identifies a first voxel included in a voxel grid array that intersects with the mesh representation. The model filling engine selects a second voxel at an exterior boundary of the voxel grid array that is not identified as a boundary voxel. The model filling engine marks the second voxel as an exterior voxel. The model filling engine marks all unmarked voxels that are adjacent to the second voxel as exterior voxels. The model filling engine marks all remaining voxels as interior voxels. A model finishing engine associated with the voxelization system generates a volumetric model based at least in part on the first voxel.

Abstract: An orthodontic appliance for movably disposed inside dental patient's mouth. The dental patient's mouth has a maxillary dental arch, a mandibular dental arch, and defines a lingual side, a labial side, and a buccal side. The orthodontic appliance has a hard maxillary retainer corresponding to patient's upper jaw, a hard mandibular retainer corresponding to patient's lower jaw, and a soft retainer rigidly attached to the hard maxillary retainer and hard mandibular retainer. The hard maxillary retainer and hard mandibular retainer can be prefabricated according to expected Cusp-to-Fossa Relationship of dental patient, and then be manufactured in an injection mold. The orthodontic appliance can have function to treat teeth deviation, dislocation, malocclusion, or teeth unmatch.

Abstract: Methods and systems for performing facial retargeting using a patch-based technique are disclosed. One or more three-dimensional (3D) representations of a source character's (e.g., a human actor's) face can be transferred onto one or more corresponding representations of a target character's (e.g., a cartoon character's) face, enabling filmmakers to transfer a performance by a source character to a target character. The source character's 3D facial shape can separated into patches. For each patch, a patch combination (representing that patch as a combination of source reference patches) can be determined. The patch combinations and target reference patches can then be used to create target patches corresponding to the target character. The target patches can be combined using an anatomical local model solver to produce a 3D facial shape corresponding to the target character, effectively transferring a facial performance by the source character to the target character.

Abstract: A method of planarizing three dimensional data of a brain implemented by a computer according to an embodiment of the present disclosure includes acquiring a three-dimensional model of the brain scanned by a scanning device, the three-dimensional model including the three-dimensional data of the brain, and mapping, in the computer, the three-dimensional model onto a circle in an area-preserving manner to form an area-preserving map. The method can convert a three-dimensional brain model into a circle or unit disc on a two-dimensional plane so that the brain model can be compared with a reference brain model, and a doctor can judge the position and degree of a brain lesion more accurately.

Abstract: The techniques described herein relate to methods, apparatus, and computer readable media configured to generate point cloud histograms. A one-dimensional histogram can be generated by determining a distance to a reference for each 3D point of a 3D point cloud. A one-dimensional histogram is generated by adding, for each histogram entry, distances that are within the entry's range of distances. A two-dimensional histogram can be determined by generating a set of orientations by determining, for each 3D point, an orientation with at least a first value for a first component and a second value for a second component. A two-dimensional histogram can be generated based on the set of orientations. Each bin can be associated with ranges of values for the first and second components. Orientations can be added for each bin that have first and second values within the first and second ranges of values, respectively, of the bin.

Abstract: Provided is a stimulation simulation method, server and, computer program using a brain model of a brain lesion patient. The stimulation simulation method using a brain model of a brain lesion patient according to various embodiments of the present invention is a stimulation simulation method using a brain model of a brain lesion patient performed by a computing device, the method includes: collecting brain images of the brain lesion patient; generating the brain model for the brain lesion patient by using the collected brain images; and simulating stimulation to the brain of the brain lesion patient by using the generated brain model.

Abstract: An automated manufacturing system for generating a graphical representation of a discrete object to be manufactured from an additively manufactured body of material. Reference feature is used to place the precursor at a subtractive manufacturing machine; the reference feature may be based on a locating feature at the subtractive manufacturing machine. Manufacturing reference feature is accomplished by automatedly detecting one or more critical-to-quality features and manufacturing the reference feature based on the one or more detected critical-to-quality features.

Abstract: Graphics processing system configured to perform ray tracing. Rays are bundled together and processed together. When differential data is needed by a shader, the data of a true ray in the bundle can be used rather than processing separate tracker rays.

Abstract: Described herein are systems, methods, and computer readable media for performing data conversion on sensor data to obtain modified sensor data that is formatted/structured appropriately for downstream processes that rely on the sensor data as input. The sensor data can include point cloud data captured by a LiDAR, for example. A grid structure and corresponding grid characteristics can be determined and the sensor data can be converted to grid-based sensor data by associating the grid structure and its characteristics with the sensor data. Generating the grid-based sensor data can include reformatting the point cloud data to superimpose the grid structure and its grid characteristics onto the point cloud data. Various downstream processing that cannot feasibly be performed on the raw sensor data can then be performed efficiently on the modified grid-based sensor data by virtue of the grid structure imbuing the sensor data with spatial proximity information.

Abstract: A computer-based method for generating a custom hand brace for a patient includes compiling optical data captured during a three-dimensional scan of a target hand of the patient into a three-dimensional hand model of the target hand; and receiving a diagnosis for an injury to the target hand of the patient. Based on the diagnosis, the method includes generating a custom hand brace model by extracting a first set of points from the three-dimensional hand model to generate an initial hand brace model; forming an interior surface of the initial hand brace model based on the first set of points; deforming the interior surface of the initial hand brace model into alignment with an exterior surface of the three-dimensional hand model to generate the custom hand brace model; and queuing the custom hand brace model for fabricating at an advanced manufacturing system.

Abstract: A method is disclosed for spinal anatomy segmentation. In one example, the method includes combining a fully convolutional network with a residual neural network. The method also includes training the combined fully convolutional network with the residual neural network from end to end. The method also includes receiving at least one medical image of a spinal anatomy. The method also includes applying the fully convolutional network with the residual neural network to at least one medical image and segmenting at least one vertebral body from the at least one medical image of the spinal anatomy.

Abstract: A point cloud model reconstruction method, an encoder, and a decoder are provided. The method includes the following. An i-th segmentation position of an i-th three-dimensional slice on a longest edge in a point cloud space is obtained, where 1?i?n?1 and n is a total number of three-dimensional slices to-be-processed. An i-th cube block set nearest to the i-th segmentation position in the i-th three-dimensional slice is determined based on the i-th segmentation position and a preset cube block length. An i-th vertex position with a cube block in the i-th cube block set is determined along the longest edge, where the i-th vertex position represents a position of a vertex on an edge which is away from a start position of the cube block by the preset cube block length. A point cloud model is reconstructed based on the i-th vertex position.

Abstract: A method and a system for determining a bite position between arch forms of a subject. The method comprises: receiving a 3D model including a first portion and a second portion respectively representative of lower and upper arch forms of the subject; determining, a respective distance value from each point of the first portion to the second portion; determining, for each point of the first portion, a respective weight value, thereby determining a respective weighted distance value; aggregating respective weighted distance values associated with each point of the first portion to determine an aggregate distance value being a remoteness measure between the first portion and the second portion; and determining the bite position based on the aggregate distance value.

Abstract: A bone density estimating method, comprising: acquiring, by an MR scanning device, a magnetic resonance, MR, sequence of a body portion, wherein the MR sequence comprises quantitative information of the body portion; generating, by a processing circuit, an MR image of the body portion based on the MR sequence, wherein each voxel of the MR image represents a volume of the body portion; identifying, by the processing circuit, a part of the MR image representing a bone portion of the body portion; for a voxel of the identified part of the MR image, estimating a bone density of a volume of the bone portion represented by the voxel, based on a quantitative value of the voxel. The quantitative information of the body portion comprises a proton density.

Abstract: A method for producing a current state model of teeth of a patient from a scan of the teeth, the method including providing an old model of the teeth including first surface elements wherein each of the first surface elements is associated with precisely one tooth of the teeth to form a segmented old model of the teeth; initially bringing the scan and the old model into a coarse alignment; thereafter determining a bounding volume of at least one of the teeth in the old model; thereafter determining second surface elements in the scan of the teeth arranged within the bounding volume; thereafter copying copies of the first surface elements associated with the at least one of the teeth from the old model into a current state model; thereafter aligning the copies in the current state model with a minimum deviation from the second surface elements.

Abstract: A learning-based clothing animation method and system for highly efficient virtual try-on simulations is provided. Given a garment, the system preprocess a rich database of physically-based dressed character simulations, for multiple body shapes and animations. Then, using a database, the system trains a learning-based model of cloth drape and wrinkles, as a function of body shape and dynamics. A model according to embodiments separates global garment fit, due to body shape, from local garment wrinkles, due to both pose dynamics and body shape. A recurrent neural network is provided to regress garment wrinkles, and the system achieves highly plausible nonlinear effects, in contrast to the blending artifacts suffered by previous methods.

Abstract: A method, executable by a processor, for planning an orthodontic treatment for a patient including determining tooth movement. The method includes obtaining a tooth and gingiva mesh from image data associated with teeth and surrounding gingiva; selecting a primary tooth to be moved to a desired position; displacing a tooth mesh of the primary tooth by a basic step distance toward the desired position determined on a jaw curve obtained for the teeth of the patient; determining if the displaced primary tooth collides with at least one secondary tooth in the desired position; in response to collision, displacing a tooth mesh of the secondary tooth away from the tooth mesh of the primary tooth by the basic step distance; and repeating determination of tooth collisions and displacing tooth contours of colliding teeth until no teeth of the teeth of the patient collide.

Abstract: A system for processing patient data associated with a joint of a patient. The system comprising a computing device executing instructions to generate a 3D patient bone model of the joint in a non-weighted pose. The instructions rearrange 3D first and second bone models in order to mimic a weighted pose of the joint of the patient from a 2D image of the joint of the patient in a weighted pose by performing the steps of: generating a plurality of 2D projections of poses of the 3D patient bone model; comparing the plurality of 2D projections to contour lines of the first bone and the second bone in the 2D image; identifying particular 2D projections that best-fit a shape and size of the contour lines; and arranging the 3D first and second bone models relative to each other according to orientations represented by the particular 2D projections that were identified.