A computer-implemented method of estimating a pose of a target object in a three-dimensional scene includes: obtaining image data and associated depth information representing a view of the three-dimensional scene; processing the image data and the associated depth information to generate a volumetric reconstruction for each of a plurality of objects in the three-dimensional scene, including the target object; determining a volumetric grid containing the target object; generating, using the generated volumetric reconstructions, occupancy data indicating portions of the volumetric grid occupied by free space and portions of the volumetric grid occupied by objects other than the target object; and estimating the pose of the target object using the generated occupancy data and pointwise feature data for a plurality of points on a surface of the target object.

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.

A three-dimensional (3D) object reconstruction neural network system learns to predict a 3D shape representation of an object from a video that includes the object. The 3D reconstruction technique may be used for content creation, such as generation of 3D characters for games, movies, and 3D printing. When 3D characters are generated from video, the content may also include motion of the character, as predicted based on the video. The 3D object construction technique exploits temporal consistency to reconstruct a dynamic 3D representation of the object from an unlabeled video. Specifically, an object in a video has a consistent shape and consistent texture across multiple frames. Texture, base shape, and part correspondence invariance constraints may be applied to fine-tune the neural network system. The reconstruction technique generalizes well—particularly for non-rigid objects.

A method for inspecting an object includes determining a first inspection package that includes a first inspection image of the object and a first designation. The method includes determining data indicative of a second inspection package that includes a second inspection image of the object and a second designation. The method includes determining a first property of the object based on the first inspection image of the object, one or more properties maps of the object, and the first designation. The method includes determining a second property of the object based on the second inspection image of the object, the one or more properties maps of the object, and the second designation. The method includes displaying the first property and the second property or displaying data indicative of a comparison of the first property with the second property.

A substantially fully-digital procurement process for government contracts that expeditiously fulfills a government entity's procurement needs within a geographical location in a fair and competitive manner. Online digital projects created using audio and video technologies allow potential bidders to easily visualize the tasks and competitively bid for them. Audio and visual features may be added to all stages—communication among stakeholders, planning of a digital project, preparation of a digital solicitation, and bidding on the solicitation—of the competitive bidding process. Substantially all project specification documents may be replaced using visual and audio technologies, and blockchain-based smart contracts to enable the government entity to digitally execute a procurement solicitation. Potential suppliers and contractors are connected on a geospatial location mapping system to expedite the procurement and add accessibility to local businesses, connect minority businesses, and create local economic sustainability. User rating makes the bidding process more transparent, fair, and competitive.

Various examples are provided related to systems and processes for generating verified wireframes corresponding to at least part of a structure or element of interest can be generated from 2D images, 3D representations (e.g., a point cloud), or a combination thereof. The wireframe can include one or more features that correspond to a structural aspect of the structure or element of interest. The verification can comprise projecting or overlaying the generated wireframe over selected 2D images and/or a point cloud that incorporates the one or more features. The wireframe can be adjusted by a user and/or a computer to align the 2D images and/or 3D representations thereto, thereby generating a verified wireframe including at least a portion of the structure or element of interest. The verified wireframes can be used to generate wireframe models, measurement information, reports, construction estimates or the like.

Methods, systems, and apparatus, including computer programs encoded on computer storage media relate to a method for generating an avatar within a video communication platform. The system may receive a selection of an avatar model from a group of one or more avatar models. The system receives a first video stream and audio data of a first video conference participant. The system analyzes image frames of the first video stream to determine a group of pixels representing the first video conference participant. The system determines a plurality of facial expression parameter associated with the determined group of pixels. Based on the determined plurality of facial expression parameter values, the system generates a first modified video stream depicting a digital representation of the first video conference participant in an avatar form.

Paired images of substantially the same scene are captured with the same freestanding sensor. The paired images include reflected light illuminated with controlled polarization states that are different between the paired images. Information from the images is applied to a convolutional neural network (CNN) configured to derive a spatially varying bi-directional reflectance distribution function (SVBRDF) for objects in the paired images. Alternatively, the sensor is fixed and oriented to capture images of an object of interest in the scene while a light source traverses a path that intersects the sensor's field of view. Information from the paired images of the scene and from the images captured of the object of interest when the light source traverses the field of view are applied to a CNN to derive a SVBDRF for the object of interest. The image information and the SVBRDF are used to render a representation with artificial lighting conditions.

A method includes receiving an image of a real environment captured using a camera worn by a user, the image comprising a hand of the user and determining a pose of the hand based on the image. Based on a three-dimensional model of the hand having the determined pose, generating a two-dimensional surface representing the hand as viewed from a first viewpoint of the user and positioning the two-dimensional surface representing the hand and one or more virtual-object representations in a three-dimensional space. The method further includes determining that a portion of the two-dimensional surface representing the hand is visible from a second viewpoint in the three-dimensional space, and generating an output image, wherein a set of image pixels of the output image corresponding to the portion of the two-dimensional surface that is visible is configured to cause a display to tur off a set of corresponding display pixels.

Methods and/or apparatus provide for obtaining intrinsics and extrinsics of a plurality of cameras arranged to capture a scene and based thereon, generate a voxel representation of the scene; obtaining extrinsics and intrinsics of a virtual camera; mapping the extrinsics and intrinsics of the virtual camera to at least one voxel surface defined in a data structure and to identify at least one camera pair suitable for obtaining depth data for that voxel surface based on the corresponding camera pair identifier; and receiving an input from the mapping unit, and in response obtaining images captured by the cameras in the at least one camera pair identified as being suitable for reconstructing the scene from the viewpoint of the virtual camera, and to generate an image of the scene from the viewpoint of the virtual camera based on the obtained images.