A method of garment deformation based on Laplacian deformation of a human body, including the following steps: inputting polygonal mesh models of the human body and the garment; discretizing non-homogeneous mesh models of the human body and the garment inputted in the first step; clustering all the discretized mesh vertices, to reduce a number of vertices and to form a set of homogeneous discrete vertices; constructing Laplacian matrices of the human body and the garment; preprocessing and solving inverse matrices; editing by using the human body mesh as a control vertex, to drive a real-time smooth deformation of the garment mesh; and mapping a deformed and simplified mesh back to a mesh space of an original resolution to obtain deformed human body and garment mesh models.

Implementations are directed to receiving a target object model representative of a target object, receiving a source object model representative of a source object, defining a set of target segments and a set of source segments using a segmentation machine learning (ML) model, for each target segment and source segment pair in a set of target segment and source segment pairs, generating a compatibility score representing a degree of similarity between a target segment and a source segment, the compatibility score calculated based on global feature representations of each of the target segment and the source segment, each global feature representation determined from a ML model, selecting a source segment for style transfer based on compatibility scores, and merging the source segment into the target object model to replace a respective target segment within the target object model and providing a stylized target object model.

The system comprises a computer server (SRC) and a data storage device (HD), the computer server (SRC) being connected to a data communication network (IT), such as the internet network, and authorizing user access. According to the invention, the system comprises a multi-dimensional type convolutive neural network (AI) ensuring indexing in a database of 3D digital models, using a neural model and a function for selecting at least one three-dimensional digital model (N3D, O3D) having at least one feature in common with an object represented by incoming 2D image data (I2D), the indexing resulting from a classification of incoming 2D image data into different classes of objects as a function of features that are recognized in the incoming 2D image data using the neural model.

A method of generating a custom three-dimensional (3D) model of a patient bone from one or more 2D images is disclosed. The method includes obtaining a 2D image of a bone, optionally of a joint, and identifying a 3D bone template for a candidate or representative bone from a pre-aligned library of representative bones. The method further includes repositioning one or more views of the 3D model or 2D images (e.g., with respect to rotation angle or caudal angle). In an iterative process, another 3D bone model for another candidate bone can be identified based on the repositioning until an accuracy threshold is satisfied. When the accuracy threshold is satisfied, surface region(s) of the current 3D bone model can then be modified to generate the resulting 3D model for the patient bone. The process can then be repeated for other bone(s) associated with the joint of the patient.

Systems and methods for creating a geometric design definition for 3D models designed to fit physical or digital template objects is disclosed. The 3D models can transform to fit specific physical or digital objects which are different from but topologically isomorphic to the original template objects based on visual or mathematical inputs. To validate the fit, the generated 3D model can be compared with the specific physical or digital objects for which the 3D model is generated to fit, and the geometry of generated 3D model can be adjusted to improve the fit if the generated 3D model is not validated. The accuracy of the fit of the generated 3D models can be improved iteratively.

Disclosed is a 3D reconstruction method for obtaining, from a 2D colour image of a human face with a visible toothed portion (1), a single reconstructed 3D surface of the toothed portion and of the facial portion (4) without toothed portion. The method comprises segmenting the 2D image into a first part (22) corresponding to the toothed portion (1) and a second part corresponding to the facial portion (4) without said toothed portion, enhancing the first part of the 2D image in order to modify the photometric characteristics, and generating a 3D surface of the face reconstructed from the enhanced first part of the 2D image and from the second part of the 2D image. The obtained 3D surface of the face is suitable for simulating a dental treatment, by substituting on the area of the 3D surface corresponding to the toothed portion (1), another 3D surface corresponding to the toothed portion after the projected treatment.

A data generation program includes instructions of: acquiring three-dimensional data representing a three-dimensional shape of a three-dimensional product; acquiring an arrangement condition for arranging a support member to the three-dimensional product; setting an extending direction, a width direction, and a height direction of the support member; adding a cutting margin of a particular thickness to a cutting surface of the three-dimensional product at one side in the height direction; setting the support member in accordance with the arrangement condition, one end of the support member in the extending direction being connected to the cutting margin added to the three-dimensional product; setting a beam, the beam being spaced from the three-dimensional product having the cutting margin in the extending direction, the beam extending in the width direction; generating three-dimensional modeling data for modeling a modeled object by using a three-dimensional modeling apparatus; and outputting the three-dimensional modeling data.

An electronic apparatus performs a method of recovering a complete and dense point cloud from a partial point cloud. The method includes: constructing a sparse but complete point cloud from the partial point cloud through a contrastive teacher-student neural network; and transforming the sparse but complete point cloud to the complete and dense point cloud. In some embodiments, the contrastive teacher-student neural network has a dual network structure comprising a teacher network and a student network both sharing the same architecture. The teacher network is a point cloud self-reconstruction network, and the student network is a point cloud completion network.

A glasses-type wearable device providing an augmented reality guide and a method for controlling the same is provided. The glasses-type wearable device includes a communication circuit, a camera, and a processor configured to receive a second surrounding-image of an external electronic device connected with the glasses-type wearable device from the external electronic device through the communication module while obtaining a first surrounding-image of the glasses-type wearable device using the camera, identify a first task being performed by a user of the glasses-type wearable device using the first surrounding-image and a second task being performed by a user of the external electronic device using the second surrounding-image, identify a difference between a current progress status of the first task and second task, and control the communication circuit to provide an AR guide corresponding to the second task to the external electronic device, based on the identified difference in progress status.

A system and method for motion retargeting based on differentiable rendering is provided. The system receives a three-dimensional (3D) skinned model of a first object and a set of images of a second object. The second object is same as or structurally similar to the first object in appearance. The system executes a differentiable rendering operation to generate a first image which includes a contour of the 3D skinned model. The system further generates a reference image which includes a contour of the second object, based on the received set of images. The system updates first values of bone parameters associated with the 3D skinned model based on a difference between the generated first image and the generated reference image. The system updates the 3D skinned model based on the updated first values of the bone parameters.