Abstract: Apparatuses, systems, and techniques are presented to generate one or more images. In at least one embodiment, one or more neural networks are used to generate one or more images of one or more objects including one or more portions of one or more other objects.

Abstract: A fractional training process can be performed training images to an instance of a machine-learned generative image model to obtain a partially trained instance of the model. A fractional optimization process can be performed with the partially trained instance to an instance of a machine-learned three-dimensional (3D) implicit representation model obtain a partially optimized instance of the model. Based on the plurality of training images, pseudo multi-view subject images can be generated with the partially optimized instance of the 3D implicit representation model and a fully trained instance of the generative image model; The partially trained instance of the model can be trained with a set of training data. The partially optimized instance of the machine-learned 3D implicit representation model can be trained with the machine-learned multi-view image model.

Abstract: A fractional training process can be performed training images to an instance of a machine-learned generative image model to obtain a partially trained instance of the model. A fractional optimization process can be performed with the partially trained instance to an instance of a machine-learned three-dimensional (3D) implicit representation model obtain a partially optimized instance of the model. Based on the plurality of training images, pseudo multi-view subject images can be generated with the partially optimized instance of the 3D implicit representation model and a fully trained instance of the generative image model; The partially trained instance of the model can be trained with a set of training data. The partially optimized instance of the machine-learned 3D implicit representation model can be trained with the machine-learned multi-view image model.

Abstract: Information defining a plurality of states, a plurality of transitions, an initial state, and a final state is received from a user. The user may also provide additional information including pre-conditions and post-conditions for one or more transitions. Context information including one or more context variables and context variable values is generated based on the information provided by the user. A first plurality of possible paths between the initial state and the final state is automatically identified, wherein each path traverses at least one state and at least one transition. A second plurality of paths is identified from among the plurality of paths, based on the context information and the pre-conditions defined by the user. A Q-value is determined for each path in the second plurality of paths, using the rewards. A path having a highest Q-value is selected and presented to the user as a BPM. An acceptance or rejection of the proposed BPM is received from the user.

Abstract: Provided is a video generation model for performing text-to-video (T2V) or other video generation techniques. The proposed model reduces the computational costs associated with video generation. In particular, unlike traditional T2V methods, the disclosed technology can generate the full temporal duration of a video clip at once, bypassing the need for extensive computation. As one example, a machine-learned denoising diffusion model can simultaneously process a plurality of noisy inputs that correspond to various timestamps spanning the temporal dimension of a video to simultaneously generate synthetic frames for the video that match the timestamps.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for editing images based on decoder-based accumulative score sampling (DASS) losses.

Abstract: A device for providing a reverse pass-through view of a user of a headset display to an onlooker includes an eyepiece comprising an optical surface configured to provide an image to a user on a first side of the optical surface. The device also includes a first camera configured to collect an image of a portion of a face of the user reflected from the optical surface in a first field of view, a display adjacent to the optical surface and configured to project forward an image of the face of the user, and a screen configured to receive light from the display and provide the image of the face of the user to an onlooker.

Abstract: A computer that includes a processor and a memory, the memory including instructions executable by the processor to generate background pixels and object pixels and generate background pixel ray data based on the background pixels and object ray pixel data based on the object pixels. The background pixel ray data can be input to a first neural network to generate background neural radiance fields (NeRFs) and the object pixel ray data can be input to a second neural network to generate object NeRFs. An output image can be rendered based on the background NeRFs and the object NeRFs.

Abstract: A method of forming a pixel-aligned volumetric avatar includes receiving multiple two-dimensional images having at least two or more fields of view of a subject. The method also includes extracting multiple image features from the two-dimensional images using a set of learnable weights, projecting the image features along a direction between a three-dimensional model of the subject and a selected observation point for a viewer, and providing, to the viewer, an image of the three-dimensional model of the subject. A system and a non-transitory, computer readable medium storing instructions to perform the above method, are also provided.

Abstract: A fractional training process can be performed training images to an instance of a machine-learned generative image model to obtain a partially trained instance of the model. A fractional optimization process can be performed with the partially trained instance to an instance of a machine-learned three-dimensional (3D) implicit representation model obtain a partially optimized instance of the model. Based on the plurality of training images, pseudo multi-view subject images can be generated with the partially optimized instance of the 3D implicit representation model and a fully trained instance of the generative image model; The partially trained instance of the model can be trained with a set of training data. The partially optimized instance of the machine-learned 3D implicit representation model can be trained with the machine-learned multi-view image model.

Abstract: A device for providing a reverse pass-through view of a user of a headset display to an onlooker includes an eyepiece comprising an optical surface configured to provide an image to a user on a first side of the optical surface. The device also includes a first camera configured to collect an image of a portion of a face of the user reflected from the optical surface in a first field of view, a display adjacent to the optical surface and configured to project forward an image of the face of the user, and a screen configured to receive light from the display and provide the image of the face of the user to an onlooker.

Abstract: In one embodiment, a method includes adjusting parameters of a three-dimensional geometry corresponding to a first person to make the three-dimensional geometry represent a desired pose for the first person, accessing a neural texture encoding an appearance of the first person, generating a first rendered neural texture based on a mapping between (1) a portion of the three-dimensional geometry that is visible from a viewing direction and (2) the neural texture, generating a second rendered neural texture by processing the first rendered neural texture using a first neural network, determining normal information associated with the portion of the three-dimensional geometry that is visible from the viewing direction, and generating a rendered image for the first person in the desired pose by processing the second rendered neural texture and the normal information using a second neural network.

Abstract: Information defining a plurality of states, a plurality of transitions, an initial state, and a final state is received from a user. The user may also provide additional information including pre-conditions and post-conditions for one or more transitions. Context information including one or more context variables and context variable values is generated based on the information provided by the user. A first plurality of possible paths between the initial state and the final state is automatically identified, wherein each path traverses at least one state and at least one transition. A second plurality of paths is identified from among the plurality of paths, based on the context information and the pre-conditions defined by the user. A Q-value is determined for each path in the second plurality of paths, using the rewards. A path having a highest Q-value is selected and presented to the user as a BPM. An acceptance or rejection of the proposed BPM is received from the user.

Abstract: A method of forming a pixel-aligned volumetric avatar includes receiving multiple two-dimensional images having at least two or more fields of view of a subject. The method also includes extracting multiple image features from the two-dimensional images using a set of learnable weights, projecting the image features along a direction between a three-dimensional model of the subject and a selected observation point for a viewer, and providing, to the viewer, an image of the three-dimensional model of the subject. A system and a non-transitory, computer readable medium storing instructions to perform the above method, are also provided.

Abstract: A device for providing a reverse pass-through view of a user of a headset display to an onlooker includes an eyepiece comprising an optical surface configured to provide an image to a user on a first side of the optical surface. The device also includes a first camera configured to collect an image of a portion of a face of the user reflected from the optical surface in a first field of view, a display adjacent to the optical surface and configured to project forward an image of the face of the user, and a screen configured to receive light from the display and provide the image of the face of the user to an onlooker.

Abstract: In one embodiment, a method includes adjusting parameters of a three-dimensional geometry corresponding to a first person to make the three-dimensional geometry represent a desired pose for the first person, accessing a neural texture encoding an appearance of the first person, generating a first rendered neural texture based on a mapping between (1) a portion of the three-dimensional geometry that is visible from a viewing direction and (2) the neural texture, generating a second rendered neural texture by processing the first rendered neural texture using a first neural network, determining normal information associated with the portion of the three-dimensional geometry that is visible from the viewing direction, and generating a rendered image for the first person in the desired pose by processing the second rendered neural texture and the normal information using a second neural network.

Abstract: Techniques for automatically converting data integration (DI) metadata between two different types of DI products are provided. According to one embodiment, a computer system can execute one or more pre-conversion tasks with respect to first DI metadata used by a first DI product, where the one or more pre-conversion tasks including exporting the first DI metadata into an intermediate format. The computer system can then convert, in an automated or semi-automated manner, the first DI metadata from the intermediate format into second DI metadata usable by a second DI product.