Abstract: Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for generating a 3D reconstruction of an object from a conditioning image of the object using a diffusion neural network system.

Abstract: The present disclosure provides a statistical, articulated 3D human shape modeling pipeline within a fully trainable, modular, deep learning framework. In particular, aspects of the present disclosure are directed to a machine-learned 3D human shape model with at least facial and body shape components that are jointly trained end-to-end on a set of training data. Joint training of the model components (e.g., including both facial, hands, and rest of body components) enables improved consistency of synthesis between the generated face and body shapes.

Abstract: The present disclosure is generally directed to reconstructing representations of bodies from images. An example method of the present disclosure includes inputting, into a machine-learned reconstruction model, input data descriptive of an image depicting a body; predicting, using a machine-learned marker prediction component of the reconstruction model, a set of surface marker locations on the body; and outputting, using a machine-learned marker poser component of the reconstruction model, an output representation of the body that corresponds to the set of surface marker locations. In the example method, one or more parameters of the reconstruction model were learned at least in part based on a consistency loss corresponding to a distance between relaxed-constraint representations generated from a prior set of surface marker locations predicted according to the one or more parameters and parametric representations generated from the prior set using kinematic constraints associated with the body.

Abstract: Systems and methods are directed to a method for estimation of an object state from image data. The method can include obtaining two-dimensional image data depicting an object. The method can include processing, with an estimation portion of a machine-learned object state estimation model, the two-dimensional image data to obtain an initial estimated state of the object. The method can include, for each of one or more refinement iterations, obtaining a previous loss value associated with a previous estimated state for the object, processing the previous loss value to obtain a current estimated state of the object, and evaluating a loss function to determine a loss value associated with the current estimated state of the object. The method can include providing a final estimated state for the object.

Abstract: The present disclosure provides a statistical, articulated 3D human shape modeling pipeline within a fully trainable, modular, deep learning framework. In particular, aspects of the present disclosure are directed to a machine-learned 3D human shape model with at least facial and body shape components that are jointly trained end-to-end on a set of training data. Joint training of the model components (e.g., including both facial, hands, and rest of body components) enables improved consistency of synthesis between the generated face and body shapes.

Abstract: The present disclosure is generally directed to reconstructing representations of bodies from images. An example method of the present disclosure includes inputting, into a machine-learned reconstruction model, input data descriptive of an image depicting a body; predicting, using a machine-learned marker prediction component of the reconstruction model, a set of surface marker locations on the body; and outputting, using a machine-learned marker poser component of the reconstruction model, an output representation of the body that corresponds to the set of surface marker locations. In the example method, one or more parameters of the reconstruction model were learned at least in part based on a consistency loss corresponding to a distance between relaxed-constraint representations generated from a prior set of surface marker locations predicted according to the one or more parameters and parametric representations generated from the prior set using kinematic constraints associated with the body.

Abstract: Systems and methods are directed to a method for estimation of an object state from image data. The method can include obtaining two-dimensional image data depicting an object. The method can include processing, with an estimation portion of a machine-learned object state estimation model, the two-dimensional image data to obtain an initial estimated state of the object. The method can include, for each of one or more refinement iterations, obtaining a previous loss value associated with a previous estimated state for the object, processing the previous loss value to obtain a current estimated state of the object, and evaluating a loss function to determine a loss value associated with the current estimated state of the object. The method can include providing a final estimated state for the object.

Abstract: The present invention is directed to generating an image based on first image data of a first person having first pose, first body shape, and first clothing and second image data of a second person having second pose, a second body shape, and second clothing. The generated image represents a transfer of appearance (e.g., clothing) of the second person to the first person. This is achieved by modeling 3d human pose and body shape for each of the persons via triangle mesh, fitting the 3d human pose and body shape models to the images of the persons, transferring appearance using barycentric methods for commonly visible vertices, and learning to color the remaining ones using deep image synthesis techniques.

Abstract: The present invention is directed to generating an image based on first image data of a first person having first pose, first body shape, and first clothing and second image data of a second person having second pose, a second body shape, and second clothing. The generated image represents a transfer of appearance (e.g., clothing) of the second person to the first person. This is achieved by modeling 3d human pose and body shape for each of the persons via triangle mesh, fitting the 3d human pose and body shape models to the images of the persons, transferring appearance using barycentric methods for commonly visible vertices, and learning to color the remaining ones using deep image synthesis techniques.